id	sid	tid	token	lemma	pos
fcis-2052	1	1	frontiers	frontier	NOUN
fcis-2052	1	2	in	in	ADP
fcis-2052	1	3	computing	computing	NOUN
fcis-2052	1	4	and	and	CCONJ
fcis-2052	1	5	intelligent	intelligent	ADJ
fcis-2052	1	6	systems	system	NOUN
fcis-2052	1	7	issn	issn	VERB
fcis-2052	1	8	:	:	PUNCT
fcis-2052	1	9	2832	2832	NUM
fcis-2052	1	10	-	-	SYM
fcis-2052	1	11	6024	6024	NUM
fcis-2052	1	12	|	|	NOUN
fcis-2052	1	13	vol	vol	NOUN
fcis-2052	1	14	.	.	PROPN
fcis-2052	2	1	1	1	NUM
fcis-2052	2	2	,	,	PUNCT
fcis-2052	2	3	no	no	INTJ
fcis-2052	2	4	.	.	NOUN
fcis-2052	2	5	3	3	NUM
fcis-2052	2	6	,	,	PUNCT
fcis-2052	2	7	2022	2022	NUM
fcis-2052	2	8	32	32	NUM
fcis-2052	2	9	design	design	NOUN
fcis-2052	2	10	of	of	ADP
fcis-2052	2	11	bad	bad	ADJ
fcis-2052	2	12	information	information	NOUN
fcis-2052	2	13	filtering	filter	VERB
fcis-2052	2	14	system	system	NOUN
fcis-2052	2	15	for	for	ADP
fcis-2052	2	16	web	web	NOUN
fcis-2052	2	17	pages	page	NOUN
fcis-2052	2	18	ronghua	ronghua	PROPN
fcis-2052	2	19	lu	lu	PROPN
fcis-2052	2	20	jingdezhen	jingdezhen	PROPN
fcis-2052	2	21	ceramic	ceramic	PROPN
fcis-2052	2	22	university	university	PROPN
fcis-2052	2	23	,	,	PUNCT
fcis-2052	2	24	jiangxi	jiangxi	NOUN
fcis-2052	2	25	,	,	PUNCT
fcis-2052	2	26	3334403	3334403	NUM
fcis-2052	2	27	,	,	PUNCT
fcis-2052	2	28	china	china	PROPN
fcis-2052	2	29	.	.	PUNCT
fcis-2052	3	1	abstract	abstract	PROPN
fcis-2052	3	2	:	:	PUNCT
fcis-2052	3	3	the	the	DET
fcis-2052	3	4	openness	openness	NOUN
fcis-2052	3	5	and	and	CCONJ
fcis-2052	3	6	globalization	globalization	NOUN
fcis-2052	3	7	of	of	ADP
fcis-2052	3	8	the	the	DET
fcis-2052	3	9	internet	internet	NOUN
fcis-2052	3	10	make	make	VERB
fcis-2052	3	11	the	the	DET
fcis-2052	3	12	information	information	NOUN
fcis-2052	3	13	spread	spread	VERB
fcis-2052	3	14	on	on	ADP
fcis-2052	3	15	the	the	DET
fcis-2052	3	16	network	network	NOUN
fcis-2052	3	17	mixed	mix	VERB
fcis-2052	3	18	,	,	PUNCT
fcis-2052	3	19	and	and	CCONJ
fcis-2052	3	20	all	all	DET
fcis-2052	3	21	kinds	kind	NOUN
fcis-2052	3	22	of	of	ADP
fcis-2052	3	23	advertisements	advertisement	NOUN
fcis-2052	3	24	,	,	PUNCT
fcis-2052	3	25	spam	spam	NOUN
fcis-2052	3	26	,	,	PUNCT
fcis-2052	3	27	reactionary	reactionary	ADJ
fcis-2052	3	28	,	,	PUNCT
fcis-2052	3	29	obscene	obscene	ADJ
fcis-2052	3	30	,	,	PUNCT
fcis-2052	3	31	violence	violence	NOUN
fcis-2052	3	32	and	and	CCONJ
fcis-2052	3	33	other	other	ADJ
fcis-2052	3	34	bad	bad	ADJ
fcis-2052	3	35	information	information	NOUN
fcis-2052	3	36	seriously	seriously	ADV
fcis-2052	3	37	interfere	interfere	VERB
fcis-2052	3	38	with	with	ADP
fcis-2052	3	39	the	the	DET
fcis-2052	3	40	normal	normal	ADJ
fcis-2052	3	41	use	use	NOUN
fcis-2052	3	42	of	of	ADP
fcis-2052	3	43	the	the	DET
fcis-2052	3	44	internet	internet	NOUN
fcis-2052	3	45	by	by	ADP
fcis-2052	3	46	internet	internet	NOUN
fcis-2052	3	47	users	user	NOUN
fcis-2052	3	48	.	.	PUNCT
fcis-2052	4	1	this	this	DET
fcis-2052	4	2	paper	paper	NOUN
fcis-2052	4	3	studies	study	VERB
fcis-2052	4	4	the	the	DET
fcis-2052	4	5	workflow	workflow	NOUN
fcis-2052	4	6	of	of	ADP
fcis-2052	4	7	the	the	DET
fcis-2052	4	8	web	web	NOUN
fcis-2052	4	9	page	page	NOUN
fcis-2052	4	10	bad	bad	ADJ
fcis-2052	4	11	information	information	NOUN
fcis-2052	4	12	filtering	filter	VERB
fcis-2052	4	13	system	system	NOUN
fcis-2052	4	14	,	,	PUNCT
fcis-2052	4	15	analyzes	analyze	VERB
fcis-2052	4	16	the	the	DET
fcis-2052	4	17	functional	functional	ADJ
fcis-2052	4	18	modules	module	NOUN
fcis-2052	4	19	of	of	ADP
fcis-2052	4	20	the	the	DET
fcis-2052	4	21	filtering	filter	VERB
fcis-2052	4	22	system	system	NOUN
fcis-2052	4	23	,	,	PUNCT
fcis-2052	4	24	and	and	CCONJ
fcis-2052	4	25	designs	design	VERB
fcis-2052	4	26	the	the	DET
fcis-2052	4	27	network	network	NOUN
fcis-2052	4	28	data	datum	NOUN
fcis-2052	4	29	processing	processing	NOUN
fcis-2052	4	30	,	,	PUNCT
fcis-2052	4	31	text	text	NOUN
fcis-2052	4	32	data	datum	NOUN
fcis-2052	4	33	processing	processing	NOUN
fcis-2052	4	34	and	and	CCONJ
fcis-2052	4	35	adaptive	adaptive	ADJ
fcis-2052	4	36	processing	processing	NOUN
fcis-2052	4	37	modules	module	NOUN
fcis-2052	4	38	in	in	ADP
fcis-2052	4	39	detail	detail	NOUN
fcis-2052	4	40	.	.	PUNCT
fcis-2052	5	1	keywords	keyword	NOUN
fcis-2052	5	2	:	:	PUNCT
fcis-2052	5	3	web	web	NOUN
fcis-2052	5	4	page	page	NOUN
fcis-2052	5	5	information	information	NOUN
fcis-2052	5	6	filtering	filtering	NOUN
fcis-2052	5	7	;	;	PUNCT
fcis-2052	5	8	network	network	NOUN
fcis-2052	5	9	data	datum	NOUN
fcis-2052	5	10	processing	processing	NOUN
fcis-2052	5	11	;	;	PUNCT
fcis-2052	5	12	text	text	NOUN
fcis-2052	5	13	data	datum	NOUN
fcis-2052	5	14	processing	processing	NOUN
fcis-2052	5	15	;	;	PUNCT
fcis-2052	5	16	chinese	chinese	ADJ
fcis-2052	5	17	word	word	NOUN
fcis-2052	5	18	segmentation	segmentation	NOUN
fcis-2052	5	19	technology	technology	NOUN
fcis-2052	5	20	;	;	PUNCT
fcis-2052	5	21	text	text	NOUN
fcis-2052	5	22	representation	representation	NOUN
fcis-2052	5	23	technology	technology	NOUN
fcis-2052	5	24	;	;	PUNCT
fcis-2052	5	25	adaptive	adaptive	ADJ
fcis-2052	5	26	processing	processing	NOUN
fcis-2052	5	27	.	.	PUNCT
fcis-2052	6	1	1	1	X
fcis-2052	6	2	.	.	X
fcis-2052	6	3	web	web	NOUN
fcis-2052	6	4	page	page	NOUN
fcis-2052	6	5	bad	bad	ADJ
fcis-2052	6	6	information	information	NOUN
fcis-2052	6	7	filtering	filter	VERB
fcis-2052	6	8	system	system	NOUN
fcis-2052	6	9	web	web	NOUN
fcis-2052	6	10	page	page	NOUN
fcis-2052	6	11	bad	bad	ADJ
fcis-2052	6	12	information	information	NOUN
fcis-2052	6	13	filtering	filter	VERB
fcis-2052	6	14	system	system	NOUN
fcis-2052	6	15	is	be	AUX
fcis-2052	6	16	content	content	NOUN
fcis-2052	6	17	-	-	PUNCT
fcis-2052	6	18	based	base	VERB
fcis-2052	6	19	filtering	filtering	NOUN
fcis-2052	6	20	,	,	PUNCT
fcis-2052	6	21	filtering	filter	VERB
fcis-2052	6	22	object	object	NOUN
fcis-2052	6	23	is	be	AUX
fcis-2052	6	24	chinese	chinese	ADJ
fcis-2052	6	25	text	text	NOUN
fcis-2052	6	26	-	-	PUNCT
fcis-2052	6	27	oriented	orient	VERB
fcis-2052	6	28	web	web	NOUN
fcis-2052	6	29	pages	page	NOUN
fcis-2052	6	30	,	,	PUNCT
fcis-2052	6	31	filtering	filter	VERB
fcis-2052	6	32	purpose	purpose	NOUN
fcis-2052	6	33	is	be	AUX
fcis-2052	6	34	topic	topic	NOUN
fcis-2052	6	35	detection	detection	NOUN
fcis-2052	6	36	.	.	PUNCT
fcis-2052	7	1	running	run	VERB
fcis-2052	7	2	on	on	ADP
fcis-2052	7	3	the	the	DET
fcis-2052	7	4	lan	lan	PROPN
fcis-2052	7	5	gateway	gateway	NOUN
fcis-2052	7	6	,	,	PUNCT
fcis-2052	7	7	the	the	DET
fcis-2052	7	8	system	system	NOUN
fcis-2052	7	9	can	can	AUX
fcis-2052	7	10	monitor	monitor	VERB
fcis-2052	7	11	incoming	incoming	ADJ
fcis-2052	7	12	web	web	NOUN
fcis-2052	7	13	pages	page	NOUN
fcis-2052	7	14	on	on	ADP
fcis-2052	7	15	the	the	DET
fcis-2052	7	16	lan	lan	PROPN
fcis-2052	7	17	,	,	PUNCT
fcis-2052	7	18	discover	discover	VERB
fcis-2052	7	19	and	and	CCONJ
fcis-2052	7	20	filter	filter	VERB
fcis-2052	7	21	the	the	DET
fcis-2052	7	22	topic	topic	NOUN
fcis-2052	7	23	information	information	NOUN
fcis-2052	7	24	specified	specify	VERB
fcis-2052	7	25	by	by	ADP
fcis-2052	7	26	the	the	DET
fcis-2052	7	27	network	network	NOUN
fcis-2052	7	28	administrator	administrator	NOUN
fcis-2052	7	29	.	.	PUNCT
fcis-2052	8	1	for	for	ADP
fcis-2052	8	2	example	example	NOUN
fcis-2052	8	3	,	,	PUNCT
fcis-2052	8	4	when	when	SCONJ
fcis-2052	8	5	enterprises	enterprise	NOUN
fcis-2052	8	6	,	,	PUNCT
fcis-2052	8	7	schools	school	NOUN
fcis-2052	8	8	and	and	CCONJ
fcis-2052	8	9	internet	internet	NOUN
fcis-2052	8	10	cafes	cafe	NOUN
fcis-2052	8	11	manage	manage	VERB
fcis-2052	8	12	the	the	DET
fcis-2052	8	13	bad	bad	ADJ
fcis-2052	8	14	information	information	NOUN
fcis-2052	8	15	in	in	ADP
fcis-2052	8	16	the	the	DET
fcis-2052	8	17	internal	internal	PROPN
fcis-2052	8	18	lan	lan	PROPN
fcis-2052	8	19	,	,	PUNCT
fcis-2052	8	20	the	the	DET
fcis-2052	8	21	system	system	NOUN
fcis-2052	8	22	can	can	AUX
fcis-2052	8	23	shield	shield	VERB
fcis-2052	8	24	information	information	NOUN
fcis-2052	8	25	such	such	ADJ
fcis-2052	8	26	as	as	ADP
fcis-2052	8	27	violence	violence	NOUN
fcis-2052	8	28	,	,	PUNCT
fcis-2052	8	29	obscenity	obscenity	NOUN
fcis-2052	8	30	and	and	CCONJ
fcis-2052	8	31	reaction	reaction	NOUN
fcis-2052	8	32	.	.	PUNCT
fcis-2052	9	1	the	the	DET
fcis-2052	9	2	topics	topic	NOUN
fcis-2052	9	3	filtered	filter	VERB
fcis-2052	9	4	by	by	ADP
fcis-2052	9	5	the	the	DET
fcis-2052	9	6	system	system	NOUN
fcis-2052	9	7	are	be	AUX
fcis-2052	9	8	initially	initially	ADV
fcis-2052	9	9	generated	generate	VERB
fcis-2052	9	10	by	by	ADP
fcis-2052	9	11	users	user	NOUN
fcis-2052	9	12	,	,	PUNCT
fcis-2052	9	13	and	and	CCONJ
fcis-2052	9	14	new	new	ADJ
fcis-2052	9	15	filtering	filter	VERB
fcis-2052	9	16	topics	topic	NOUN
fcis-2052	9	17	can	can	AUX
fcis-2052	9	18	be	be	AUX
fcis-2052	9	19	regenerated	regenerate	VERB
fcis-2052	9	20	as	as	SCONJ
fcis-2052	9	21	needed	need	VERB
fcis-2052	9	22	during	during	ADP
fcis-2052	9	23	filtering	filter	VERB
fcis-2052	9	24	implementation	implementation	NOUN
fcis-2052	9	25	.	.	PUNCT
fcis-2052	10	1	in	in	ADP
fcis-2052	10	2	the	the	DET
fcis-2052	10	3	experiment	experiment	NOUN
fcis-2052	10	4	,	,	PUNCT
fcis-2052	10	5	we	we	PRON
fcis-2052	10	6	selected	select	VERB
fcis-2052	10	7	the	the	DET
fcis-2052	10	8	knowledge	knowledge	NOUN
fcis-2052	10	9	of	of	ADP
fcis-2052	10	10	sexual	sexual	ADJ
fcis-2052	10	11	medicine	medicine	NOUN
fcis-2052	10	12	as	as	ADP
fcis-2052	10	13	the	the	DET
fcis-2052	10	14	filtering	filtering	NOUN
fcis-2052	10	15	theme	theme	NOUN
fcis-2052	10	16	.	.	PUNCT
fcis-2052	11	1	for	for	ADP
fcis-2052	11	2	the	the	DET
fcis-2052	11	3	filtered	filter	VERB
fcis-2052	11	4	documents	document	NOUN
fcis-2052	11	5	,	,	PUNCT
fcis-2052	11	6	a	a	DET
fcis-2052	11	7	feedback	feedback	NOUN
fcis-2052	11	8	mechanism	mechanism	NOUN
fcis-2052	11	9	is	be	AUX
fcis-2052	11	10	provided	provide	VERB
fcis-2052	11	11	,	,	PUNCT
fcis-2052	11	12	and	and	CCONJ
fcis-2052	11	13	the	the	DET
fcis-2052	11	14	finally	finally	ADV
fcis-2052	11	15	determined	determine	VERB
fcis-2052	11	16	group	group	NOUN
fcis-2052	11	17	is	be	AUX
fcis-2052	11	18	imported	import	VERB
fcis-2052	11	19	into	into	ADP
fcis-2052	11	20	the	the	DET
fcis-2052	11	21	template	template	NOUN
fcis-2052	11	22	training	training	NOUN
fcis-2052	11	23	library	library	NOUN
fcis-2052	11	24	,	,	PUNCT
fcis-2052	11	25	and	and	CCONJ
fcis-2052	11	26	the	the	DET
fcis-2052	11	27	user	user	NOUN
fcis-2052	11	28	's	's	PART
fcis-2052	11	29	intention	intention	NOUN
fcis-2052	11	30	is	be	AUX
fcis-2052	11	31	tracked	track	VERB
fcis-2052	11	32	and	and	CCONJ
fcis-2052	11	33	learned	learn	VERB
fcis-2052	11	34	through	through	ADP
fcis-2052	11	35	genetic	genetic	ADJ
fcis-2052	11	36	algorithm	algorithm	NOUN
fcis-2052	11	37	to	to	PART
fcis-2052	11	38	generate	generate	VERB
fcis-2052	11	39	more	more	ADV
fcis-2052	11	40	accurate	accurate	ADJ
fcis-2052	11	41	user	user	NOUN
fcis-2052	11	42	templates	template	NOUN
fcis-2052	11	43	.	.	PUNCT
fcis-2052	12	1	the	the	DET
fcis-2052	12	2	web	web	NOUN
fcis-2052	12	3	page	page	NOUN
fcis-2052	12	4	bad	bad	ADJ
fcis-2052	12	5	information	information	NOUN
fcis-2052	12	6	filtering	filter	VERB
fcis-2052	12	7	system	system	NOUN
fcis-2052	12	8	should	should	AUX
fcis-2052	12	9	deal	deal	VERB
fcis-2052	12	10	with	with	ADP
fcis-2052	12	11	the	the	DET
fcis-2052	12	12	following	follow	VERB
fcis-2052	12	13	transactions	transaction	NOUN
fcis-2052	12	14	in	in	ADP
fcis-2052	12	15	each	each	DET
fcis-2052	12	16	stage	stage	NOUN
fcis-2052	12	17	:	:	PUNCT
fcis-2052	12	18	1	1	X
fcis-2052	12	19	)	)	PUNCT
fcis-2052	12	20	information	information	NOUN
fcis-2052	12	21	acquisition	acquisition	NOUN
fcis-2052	12	22	stage	stage	NOUN
fcis-2052	12	23	:	:	PUNCT
fcis-2052	12	24	network	network	NOUN
fcis-2052	12	25	information	information	NOUN
fcis-2052	12	26	filtering	filtering	NOUN
fcis-2052	12	27	is	be	AUX
fcis-2052	12	28	based	base	VERB
fcis-2052	12	29	on	on	ADP
fcis-2052	12	30	packet	packet	NOUN
fcis-2052	12	31	capture	capture	NOUN
fcis-2052	12	32	.	.	PUNCT
fcis-2052	13	1	information	information	NOUN
fcis-2052	13	2	acquisition	acquisition	NOUN
fcis-2052	13	3	requires	require	VERB
fcis-2052	13	4	capturing	capture	VERB
fcis-2052	13	5	http	http	ADJ
fcis-2052	13	6	packets	packet	NOUN
fcis-2052	13	7	in	in	ADP
fcis-2052	13	8	the	the	DET
fcis-2052	13	9	network	network	NOUN
fcis-2052	13	10	and	and	CCONJ
fcis-2052	13	11	parsing	parse	VERB
fcis-2052	13	12	the	the	DET
fcis-2052	13	13	packets	packet	NOUN
fcis-2052	13	14	into	into	ADP
fcis-2052	13	15	a	a	DET
fcis-2052	13	16	text	text	NOUN
fcis-2052	13	17	format	format	NOUN
fcis-2052	13	18	for	for	ADP
fcis-2052	13	19	processing	processing	NOUN
fcis-2052	13	20	according	accord	VERB
fcis-2052	13	21	to	to	ADP
fcis-2052	13	22	ip	ip	PROPN
fcis-2052	13	23	,	,	PUNCT
fcis-2052	13	24	tcp	tcp	ADJ
fcis-2052	13	25	,	,	PUNCT
fcis-2052	13	26	and	and	CCONJ
fcis-2052	13	27	http	http	ADJ
fcis-2052	13	28	protocols	protocol	NOUN
fcis-2052	13	29	.	.	PUNCT
fcis-2052	14	1	2	2	X
fcis-2052	14	2	)	)	PUNCT
fcis-2052	14	3	information	information	NOUN
fcis-2052	14	4	representation	representation	NOUN
fcis-2052	14	5	stage	stage	NOUN
fcis-2052	14	6	:	:	PUNCT
fcis-2052	14	7	process	process	VERB
fcis-2052	14	8	the	the	DET
fcis-2052	14	9	text	text	NOUN
fcis-2052	14	10	obtained	obtain	VERB
fcis-2052	14	11	from	from	ADP
fcis-2052	14	12	the	the	DET
fcis-2052	14	13	information	information	NOUN
fcis-2052	14	14	acquisition	acquisition	NOUN
fcis-2052	14	15	stage	stage	NOUN
fcis-2052	14	16	,	,	PUNCT
fcis-2052	14	17	extract	extract	VERB
fcis-2052	14	18	the	the	DET
fcis-2052	14	19	keywords	keyword	NOUN
fcis-2052	14	20	that	that	PRON
fcis-2052	14	21	can	can	AUX
fcis-2052	14	22	represent	represent	VERB
fcis-2052	14	23	the	the	DET
fcis-2052	14	24	characteristics	characteristic	NOUN
fcis-2052	14	25	of	of	ADP
fcis-2052	14	26	the	the	DET
fcis-2052	14	27	document	document	NOUN
fcis-2052	14	28	and	and	CCONJ
fcis-2052	14	29	calculate	calculate	VERB
fcis-2052	14	30	the	the	DET
fcis-2052	14	31	weights	weight	NOUN
fcis-2052	14	32	.	.	PUNCT
fcis-2052	15	1	since	since	SCONJ
fcis-2052	15	2	there	there	PRON
fcis-2052	15	3	is	be	VERB
fcis-2052	15	4	no	no	DET
fcis-2052	15	5	obvious	obvious	ADJ
fcis-2052	15	6	separator	separator	NOUN
fcis-2052	15	7	in	in	ADP
fcis-2052	15	8	chinese	chinese	ADJ
fcis-2052	15	9	documents	document	NOUN
fcis-2052	15	10	,	,	PUNCT
fcis-2052	15	11	word	word	NOUN
fcis-2052	15	12	segmentation	segmentation	NOUN
fcis-2052	15	13	should	should	AUX
fcis-2052	15	14	be	be	AUX
fcis-2052	15	15	carried	carry	VERB
fcis-2052	15	16	out	out	ADP
fcis-2052	15	17	before	before	ADP
fcis-2052	15	18	feature	feature	NOUN
fcis-2052	15	19	extraction.3	extraction.3	PROPN
fcis-2052	15	20	)	)	PUNCT
fcis-2052	15	21	matching	matching	NOUN
fcis-2052	15	22	stage	stage	NOUN
fcis-2052	15	23	:	:	PUNCT
fcis-2052	15	24	the	the	DET
fcis-2052	15	25	text	text	NOUN
fcis-2052	15	26	representation	representation	NOUN
fcis-2052	15	27	of	of	ADP
fcis-2052	15	28	the	the	DET
fcis-2052	15	29	unknown	unknown	ADJ
fcis-2052	15	30	document	document	NOUN
fcis-2052	15	31	is	be	AUX
fcis-2052	15	32	matched	match	VERB
fcis-2052	15	33	with	with	ADP
fcis-2052	15	34	the	the	DET
fcis-2052	15	35	known	know	VERB
fcis-2052	15	36	user	user	NOUN
fcis-2052	15	37	template	template	NOUN
fcis-2052	15	38	(	(	PUNCT
fcis-2052	15	39	knowledge	knowledge	NOUN
fcis-2052	15	40	pattern	pattern	NOUN
fcis-2052	15	41	)	)	PUNCT
fcis-2052	15	42	.	.	PUNCT
fcis-2052	16	1	the	the	DET
fcis-2052	16	2	similarity	similarity	NOUN
fcis-2052	16	3	of	of	ADP
fcis-2052	16	4	the	the	DET
fcis-2052	16	5	vector	vector	NOUN
fcis-2052	16	6	space	space	NOUN
fcis-2052	16	7	model	model	NOUN
fcis-2052	16	8	is	be	AUX
fcis-2052	16	9	used	use	VERB
fcis-2052	16	10	to	to	PART
fcis-2052	16	11	calculate	calculate	VERB
fcis-2052	16	12	the	the	DET
fcis-2052	16	13	correlation	correlation	NOUN
fcis-2052	16	14	between	between	ADP
fcis-2052	16	15	the	the	DET
fcis-2052	16	16	unknown	unknown	ADJ
fcis-2052	16	17	document	document	NOUN
fcis-2052	16	18	and	and	CCONJ
fcis-2052	16	19	the	the	DET
fcis-2052	16	20	actual	actual	ADJ
fcis-2052	16	21	demand	demand	NOUN
fcis-2052	16	22	.	.	PUNCT
fcis-2052	17	1	after	after	ADP
fcis-2052	17	2	reaching	reach	VERB
fcis-2052	17	3	a	a	DET
fcis-2052	17	4	certain	certain	ADJ
fcis-2052	17	5	threshold	threshold	NOUN
fcis-2052	17	6	,	,	PUNCT
fcis-2052	17	7	the	the	DET
fcis-2052	17	8	unknown	unknown	ADJ
fcis-2052	17	9	document	document	NOUN
fcis-2052	17	10	is	be	AUX
fcis-2052	17	11	identified	identify	VERB
fcis-2052	17	12	.	.	PUNCT
fcis-2052	18	1	4	4	X
fcis-2052	18	2	)	)	PUNCT
fcis-2052	18	3	information	information	NOUN
fcis-2052	18	4	classification	classification	NOUN
fcis-2052	18	5	stage	stage	NOUN
fcis-2052	18	6	:	:	PUNCT
fcis-2052	18	7	through	through	ADP
fcis-2052	18	8	system	system	NOUN
fcis-2052	18	9	identification	identification	NOUN
fcis-2052	18	10	and	and	CCONJ
fcis-2052	18	11	user	user	NOUN
fcis-2052	18	12	feedback	feedback	NOUN
fcis-2052	18	13	on	on	ADP
fcis-2052	18	14	identification	identification	NOUN
fcis-2052	18	15	results	result	NOUN
fcis-2052	18	16	,	,	PUNCT
fcis-2052	18	17	the	the	DET
fcis-2052	18	18	documents	document	NOUN
fcis-2052	18	19	are	be	AUX
fcis-2052	18	20	input	input	VERB
fcis-2052	18	21	into	into	ADP
fcis-2052	18	22	the	the	DET
fcis-2052	18	23	corresponding	correspond	VERB
fcis-2052	18	24	document	document	NOUN
fcis-2052	18	25	set	set	VERB
fcis-2052	18	26	to	to	PART
fcis-2052	18	27	facilitate	facilitate	VERB
fcis-2052	18	28	the	the	DET
fcis-2052	18	29	reconstruction	reconstruction	NOUN
fcis-2052	18	30	of	of	ADP
fcis-2052	18	31	user	user	NOUN
fcis-2052	18	32	templates	template	NOUN
fcis-2052	18	33	.	.	PUNCT
fcis-2052	19	1	5	5	X
fcis-2052	19	2	)	)	PUNCT
fcis-2052	19	3	knowledge	knowledge	NOUN
fcis-2052	19	4	mode	mode	NOUN
fcis-2052	19	5	:	:	PUNCT
fcis-2052	19	6	that	that	PRON
fcis-2052	19	7	is	is	ADV
fcis-2052	19	8	,	,	PUNCT
fcis-2052	19	9	the	the	DET
fcis-2052	19	10	establishment	establishment	NOUN
fcis-2052	19	11	and	and	CCONJ
fcis-2052	19	12	update	update	NOUN
fcis-2052	19	13	of	of	ADP
fcis-2052	19	14	user	user	NOUN
fcis-2052	19	15	templates	template	NOUN
fcis-2052	19	16	.	.	PUNCT
fcis-2052	20	1	the	the	DET
fcis-2052	20	2	system	system	NOUN
fcis-2052	20	3	established	establish	VERB
fcis-2052	20	4	a	a	DET
fcis-2052	20	5	learning	learning	NOUN
fcis-2052	20	6	evolution	evolution	NOUN
fcis-2052	20	7	mechanism	mechanism	NOUN
fcis-2052	20	8	,	,	PUNCT
fcis-2052	20	9	according	accord	VERB
fcis-2052	20	10	to	to	ADP
fcis-2052	20	11	the	the	DET
fcis-2052	20	12	user	user	NOUN
fcis-2052	20	13	feedback	feedback	NOUN
fcis-2052	20	14	,	,	PUNCT
fcis-2052	20	15	the	the	DET
fcis-2052	20	16	user	user	NOUN
fcis-2052	20	17	template	template	NOUN
fcis-2052	20	18	to	to	PART
fcis-2052	20	19	learn	learn	VERB
fcis-2052	20	20	genetic	genetic	ADJ
fcis-2052	20	21	algorithm	algorithm	NOUN
fcis-2052	20	22	,	,	PUNCT
fcis-2052	20	23	to	to	PART
fcis-2052	20	24	improve	improve	VERB
fcis-2052	20	25	the	the	DET
fcis-2052	20	26	adaptive	adaptive	ADJ
fcis-2052	20	27	ability	ability	NOUN
fcis-2052	20	28	of	of	ADP
fcis-2052	20	29	the	the	DET
fcis-2052	20	30	system	system	NOUN
fcis-2052	20	31	.	.	PUNCT
fcis-2052	21	1	2	2	X
fcis-2052	21	2	.	.	X
fcis-2052	21	3	2.design	2.design	NUM
fcis-2052	21	4	of	of	ADP
fcis-2052	21	5	bad	bad	ADJ
fcis-2052	21	6	information	information	NOUN
fcis-2052	21	7	filtering	filter	VERB
fcis-2052	21	8	system	system	NOUN
fcis-2052	21	9	for	for	ADP
fcis-2052	21	10	web	web	NOUN
fcis-2052	21	11	pages	page	NOUN
fcis-2052	21	12	the	the	DET
fcis-2052	21	13	performance	performance	NOUN
fcis-2052	21	14	of	of	ADP
fcis-2052	21	15	the	the	DET
fcis-2052	21	16	information	information	NOUN
fcis-2052	21	17	filtering	filter	VERB
fcis-2052	21	18	system	system	NOUN
fcis-2052	21	19	is	be	AUX
fcis-2052	21	20	mainly	mainly	ADV
fcis-2052	21	21	reflected	reflect	VERB
fcis-2052	21	22	in	in	ADP
fcis-2052	21	23	the	the	DET
fcis-2052	21	24	accuracy	accuracy	NOUN
fcis-2052	21	25	of	of	ADP
fcis-2052	21	26	filtering	filtering	NOUN
fcis-2052	21	27	.	.	PUNCT
fcis-2052	22	1	the	the	DET
fcis-2052	22	2	main	main	ADJ
fcis-2052	22	3	reason	reason	NOUN
fcis-2052	22	4	why	why	SCONJ
fcis-2052	22	5	the	the	DET
fcis-2052	22	6	filtering	filter	VERB
fcis-2052	22	7	system	system	NOUN
fcis-2052	22	8	is	be	AUX
fcis-2052	22	9	unreliable	unreliable	ADJ
fcis-2052	22	10	is	be	AUX
fcis-2052	22	11	the	the	DET
fcis-2052	22	12	accuracy	accuracy	NOUN
fcis-2052	22	13	of	of	ADP
fcis-2052	22	14	user	user	NOUN
fcis-2052	22	15	templates	template	NOUN
fcis-2052	22	16	.	.	PUNCT
fcis-2052	23	1	however	however	ADV
fcis-2052	23	2	,	,	PUNCT
fcis-2052	23	3	the	the	DET
fcis-2052	23	4	rapid	rapid	ADJ
fcis-2052	23	5	changes	change	NOUN
fcis-2052	23	6	of	of	ADP
fcis-2052	23	7	knowledge	knowledge	NOUN
fcis-2052	23	8	and	and	CCONJ
fcis-2052	23	9	information	information	NOUN
fcis-2052	23	10	and	and	CCONJ
fcis-2052	23	11	the	the	DET
fcis-2052	23	12	instability	instability	NOUN
fcis-2052	23	13	of	of	ADP
fcis-2052	23	14	user	user	NOUN
fcis-2052	23	15	requirements	requirement	NOUN
fcis-2052	23	16	determine	determine	VERB
fcis-2052	23	17	that	that	SCONJ
fcis-2052	23	18	user	user	NOUN
fcis-2052	23	19	templates	template	NOUN
fcis-2052	23	20	need	need	VERB
fcis-2052	23	21	to	to	PART
fcis-2052	23	22	be	be	AUX
fcis-2052	23	23	updated	update	VERB
fcis-2052	23	24	constantly	constantly	ADV
fcis-2052	23	25	.	.	PUNCT
fcis-2052	24	1	the	the	DET
fcis-2052	24	2	bad	bad	ADJ
fcis-2052	24	3	information	information	NOUN
fcis-2052	24	4	filtering	filter	VERB
fcis-2052	24	5	system	system	NOUN
fcis-2052	24	6	of	of	ADP
fcis-2052	24	7	the	the	DET
fcis-2052	24	8	web	web	NOUN
fcis-2052	24	9	page	page	NOUN
fcis-2052	24	10	has	have	AUX
fcis-2052	24	11	fully	fully	ADV
fcis-2052	24	12	considered	consider	VERB
fcis-2052	24	13	the	the	DET
fcis-2052	24	14	improvement	improvement	NOUN
fcis-2052	24	15	requirements	requirement	NOUN
fcis-2052	24	16	of	of	ADP
fcis-2052	24	17	the	the	DET
fcis-2052	24	18	system	system	NOUN
fcis-2052	24	19	in	in	ADP
fcis-2052	24	20	the	the	DET
fcis-2052	24	21	design	design	NOUN
fcis-2052	24	22	,	,	PUNCT
fcis-2052	24	23	and	and	CCONJ
fcis-2052	24	24	will	will	AUX
fcis-2052	24	25	continuously	continuously	ADV
fcis-2052	24	26	optimize	optimize	VERB
fcis-2052	24	27	the	the	DET
fcis-2052	24	28	user	user	NOUN
fcis-2052	24	29	template	template	NOUN
fcis-2052	24	30	in	in	ADP
fcis-2052	24	31	operation	operation	NOUN
fcis-2052	24	32	to	to	PART
fcis-2052	24	33	improve	improve	VERB
fcis-2052	24	34	the	the	DET
fcis-2052	24	35	accuracy	accuracy	NOUN
fcis-2052	24	36	of	of	ADP
fcis-2052	24	37	filtering	filtering	NOUN
fcis-2052	24	38	.	.	PUNCT
fcis-2052	25	1	the	the	DET
fcis-2052	25	2	overall	overall	ADJ
fcis-2052	25	3	design	design	NOUN
fcis-2052	25	4	of	of	ADP
fcis-2052	25	5	the	the	DET
fcis-2052	25	6	system	system	NOUN
fcis-2052	25	7	is	be	AUX
fcis-2052	25	8	shown	show	VERB
fcis-2052	25	9	in	in	ADP
fcis-2052	25	10	figure	figure	NOUN
fcis-2052	25	11	1	1	NUM
fcis-2052	25	12	.	.	PUNCT
fcis-2052	25	13	figure	figure	NOUN
fcis-2052	25	14	1	1	NUM
fcis-2052	25	15	.	.	PUNCT
fcis-2052	26	1	design	design	NOUN
fcis-2052	26	2	of	of	ADP
fcis-2052	26	3	web	web	NOUN
fcis-2052	26	4	page	page	NOUN
fcis-2052	26	5	bad	bad	ADJ
fcis-2052	26	6	information	information	NOUN
fcis-2052	26	7	filtering	filter	VERB
fcis-2052	26	8	system	system	NOUN
fcis-2052	26	9	first	first	ADV
fcis-2052	26	10	,	,	PUNCT
fcis-2052	26	11	build	build	VERB
fcis-2052	26	12	the	the	DET
fcis-2052	26	13	basic	basic	ADJ
fcis-2052	26	14	"	"	PUNCT
fcis-2052	26	15	dictionary	dictionary	ADJ
fcis-2052	26	16	database	database	NOUN
fcis-2052	26	17	"	"	PUNCT
fcis-2052	26	18	and	and	CCONJ
fcis-2052	26	19	"	"	PUNCT
fcis-2052	26	20	user	user	NOUN
fcis-2052	26	21	template	template	NOUN
fcis-2052	26	22	"	"	PUNCT
fcis-2052	26	23	.	.	PUNCT
fcis-2052	27	1	dictionary	dictionary	ADJ
fcis-2052	27	2	database	database	NOUN
fcis-2052	27	3	includes	include	VERB
fcis-2052	27	4	word	word	NOUN
fcis-2052	27	5	segmentation	segmentation	NOUN
fcis-2052	27	6	database	database	NOUN
fcis-2052	27	7	and	and	CCONJ
fcis-2052	27	8	stop	stop	VERB
fcis-2052	27	9	word	word	NOUN
fcis-2052	27	10	database	database	NOUN
fcis-2052	27	11	.	.	PUNCT
fcis-2052	28	1	stop	stop	VERB
fcis-2052	28	2	words	word	NOUN
fcis-2052	28	3	are	be	AUX
fcis-2052	28	4	generally	generally	ADV
fcis-2052	28	5	selected	select	VERB
fcis-2052	28	6	as	as	ADP
fcis-2052	28	7	words	word	NOUN
fcis-2052	28	8	that	that	PRON
fcis-2052	28	9	appear	appear	VERB
fcis-2052	28	10	frequently	frequently	ADV
fcis-2052	28	11	in	in	ADP
fcis-2052	28	12	all	all	DET
fcis-2052	28	13	documents	document	NOUN
fcis-2052	28	14	,	,	PUNCT
fcis-2052	28	15	but	but	CCONJ
fcis-2052	28	16	contribute	contribute	VERB
fcis-2052	28	17	little	little	ADJ
fcis-2052	28	18	to	to	ADP
fcis-2052	28	19	the	the	DET
fcis-2052	28	20	topic	topic	NOUN
fcis-2052	28	21	of	of	ADP
fcis-2052	28	22	the	the	DET
fcis-2052	28	23	document	document	NOUN
fcis-2052	28	24	's	's	PART
fcis-2052	28	25	content	content	NOUN
fcis-2052	28	26	.	.	PUNCT
fcis-2052	29	1	the	the	DET
fcis-2052	29	2	establishment	establishment	NOUN
fcis-2052	29	3	of	of	ADP
fcis-2052	29	4	initial	initial	ADJ
fcis-2052	29	5	user	user	NOUN
fcis-2052	29	6	template	template	NOUN
fcis-2052	29	7	is	be	AUX
fcis-2052	29	8	to	to	PART
fcis-2052	29	9	manually	manually	ADV
fcis-2052	29	10	select	select	VERB
fcis-2052	29	11	several	several	ADJ
fcis-2052	29	12	documents	document	NOUN
fcis-2052	29	13	that	that	PRON
fcis-2052	29	14	can	can	AUX
fcis-2052	29	15	represent	represent	VERB
fcis-2052	29	16	this	this	DET
fcis-2052	29	17	category	category	NOUN
fcis-2052	29	18	,	,	PUNCT
fcis-2052	29	19	and	and	CCONJ
fcis-2052	29	20	generate	generate	VERB
fcis-2052	29	21	the	the	DET
fcis-2052	29	22	vector	vector	NOUN
fcis-2052	29	23	space	space	NOUN
fcis-2052	29	24	expression	expression	NOUN
fcis-2052	29	25	of	of	ADP
fcis-2052	29	26	this	this	DET
fcis-2052	29	27	category	category	NOUN
fcis-2052	29	28	document	document	NOUN
fcis-2052	29	29	through	through	ADP
fcis-2052	29	30	training	training	NOUN
fcis-2052	29	31	.	.	PUNCT
fcis-2052	30	1	then	then	ADV
fcis-2052	30	2	test	test	VERB
fcis-2052	30	3	a	a	DET
fcis-2052	30	4	batch	batch	NOUN
fcis-2052	30	5	of	of	ADP
fcis-2052	30	6	related	related	ADJ
fcis-2052	30	7	and	and	CCONJ
fcis-2052	30	8	unrelated	unrelated	ADJ
fcis-2052	30	9	documents	document	NOUN
fcis-2052	30	10	to	to	PART
fcis-2052	30	11	determine	determine	VERB
fcis-2052	30	12	the	the	DET
fcis-2052	30	13	threshold	threshold	NOUN
fcis-2052	30	14	of	of	ADP
fcis-2052	30	15	similarity	similarity	NOUN
fcis-2052	30	16	that	that	PRON
fcis-2052	30	17	can	can	AUX
fcis-2052	30	18	match	match	VERB
fcis-2052	30	19	the	the	DET
fcis-2052	30	20	category	category	NOUN
fcis-2052	30	21	.	.	PUNCT
fcis-2052	31	1	the	the	DET
fcis-2052	31	2	functions	function	NOUN
fcis-2052	31	3	of	of	ADP
fcis-2052	31	4	each	each	DET
fcis-2052	31	5	module	module	NOUN
fcis-2052	31	6	of	of	ADP
fcis-2052	31	7	33	33	NUM
fcis-2052	31	8	the	the	DET
fcis-2052	31	9	system	system	NOUN
fcis-2052	31	10	are	be	AUX
fcis-2052	31	11	as	as	SCONJ
fcis-2052	31	12	follows	follow	VERB
fcis-2052	31	13	:	:	PUNCT
fcis-2052	31	14	1	1	NUM
fcis-2052	31	15	)	)	PUNCT
fcis-2052	31	16	network	network	NOUN
fcis-2052	31	17	packet	packet	NOUN
fcis-2052	31	18	parsing	parsing	NOUN
fcis-2052	31	19	:	:	PUNCT
fcis-2052	31	20	capture	capture	VERB
fcis-2052	31	21	ethernet	ethernet	NOUN
fcis-2052	31	22	frames	frame	NOUN
fcis-2052	31	23	in	in	ADP
fcis-2052	31	24	the	the	DET
fcis-2052	31	25	lan	lan	PROPN
fcis-2052	31	26	,	,	PUNCT
fcis-2052	31	27	filter	filter	VERB
fcis-2052	31	28	out	out	ADP
fcis-2052	31	29	tcp	tcp	VERB
fcis-2052	31	30	packets	packet	NOUN
fcis-2052	31	31	containing	contain	VERB
fcis-2052	31	32	http	http	ADJ
fcis-2052	31	33	text	text	NOUN
fcis-2052	31	34	information	information	NOUN
fcis-2052	31	35	,	,	PUNCT
fcis-2052	31	36	and	and	CCONJ
fcis-2052	31	37	screen	screen	NOUN
fcis-2052	31	38	and	and	CCONJ
fcis-2052	31	39	filter	filter	NOUN
fcis-2052	31	40	pages	page	NOUN
fcis-2052	31	41	with	with	ADP
fcis-2052	31	42	the	the	DET
fcis-2052	31	43	same	same	ADJ
fcis-2052	31	44	link	link	NOUN
fcis-2052	31	45	address	address	NOUN
fcis-2052	31	46	as	as	ADP
fcis-2052	31	47	those	those	PRON
fcis-2052	31	48	in	in	ADP
fcis-2052	31	49	the	the	DET
fcis-2052	31	50	url	url	NOUN
fcis-2052	31	51	database	database	NOUN
fcis-2052	31	52	.	.	PUNCT
fcis-2052	32	1	in	in	ADP
fcis-2052	32	2	the	the	DET
fcis-2052	32	3	filtering	filter	VERB
fcis-2052	32	4	mode	mode	NOUN
fcis-2052	32	5	,	,	PUNCT
fcis-2052	32	6	a	a	DET
fcis-2052	32	7	socket	socket	NOUN
fcis-2052	32	8	is	be	AUX
fcis-2052	32	9	set	set	VERB
fcis-2052	32	10	up	up	ADP
fcis-2052	32	11	to	to	PART
fcis-2052	32	12	intercept	intercept	VERB
fcis-2052	32	13	the	the	DET
fcis-2052	32	14	packet	packet	NOUN
fcis-2052	32	15	and	and	CCONJ
fcis-2052	32	16	forward	forward	ADV
fcis-2052	32	17	the	the	DET
fcis-2052	32	18	packet	packet	NOUN
fcis-2052	32	19	so	so	SCONJ
fcis-2052	32	20	that	that	SCONJ
fcis-2052	32	21	the	the	DET
fcis-2052	32	22	message	message	NOUN
fcis-2052	32	23	"	"	PUNCT
fcis-2052	32	24	this	this	DET
fcis-2052	32	25	message	message	NOUN
fcis-2052	32	26	is	be	AUX
fcis-2052	32	27	intercepted	intercept	VERB
fcis-2052	32	28	"	"	PUNCT
fcis-2052	32	29	is	be	AUX
fcis-2052	32	30	displayed	display	VERB
fcis-2052	32	31	on	on	ADP
fcis-2052	32	32	the	the	DET
fcis-2052	32	33	terminal	terminal	ADJ
fcis-2052	32	34	user	user	NOUN
fcis-2052	32	35	interface	interface	NOUN
fcis-2052	32	36	.	.	PUNCT
fcis-2052	33	1	this	this	DET
fcis-2052	33	2	module	module	NOUN
fcis-2052	33	3	is	be	AUX
fcis-2052	33	4	also	also	ADV
fcis-2052	33	5	responsible	responsible	ADJ
fcis-2052	33	6	for	for	ADP
fcis-2052	33	7	message	message	NOUN
fcis-2052	33	8	parsing	parsing	NOUN
fcis-2052	33	9	and	and	CCONJ
fcis-2052	33	10	web	web	NOUN
fcis-2052	33	11	page	page	NOUN
fcis-2052	33	12	reorganization	reorganization	NOUN
fcis-2052	33	13	of	of	ADP
fcis-2052	33	14	the	the	DET
fcis-2052	33	15	extracted	extract	VERB
fcis-2052	33	16	http	http	ADJ
fcis-2052	33	17	packets	packet	NOUN
fcis-2052	33	18	,	,	PUNCT
fcis-2052	33	19	and	and	CCONJ
fcis-2052	33	20	the	the	DET
fcis-2052	33	21	complete	complete	ADJ
fcis-2052	33	22	web	web	NOUN
fcis-2052	33	23	page	page	NOUN
fcis-2052	33	24	is	be	AUX
fcis-2052	33	25	passed	pass	VERB
fcis-2052	33	26	to	to	ADP
fcis-2052	33	27	the	the	DET
fcis-2052	33	28	"	"	PUNCT
fcis-2052	33	29	web	web	NOUN
fcis-2052	33	30	page	page	NOUN
fcis-2052	33	31	text	text	NOUN
fcis-2052	33	32	parsing	parsing	NOUN
fcis-2052	33	33	"	"	PUNCT
fcis-2052	33	34	module	module	NOUN
fcis-2052	33	35	.	.	NOUN
fcis-2052	34	1	2	2	NUM
fcis-2052	34	2	)	)	PUNCT
fcis-2052	34	3	web	web	NOUN
fcis-2052	34	4	page	page	NOUN
fcis-2052	34	5	text	text	NOUN
fcis-2052	34	6	parsing	parsing	NOUN
fcis-2052	34	7	:	:	PUNCT
fcis-2052	34	8	convert	convert	VERB
fcis-2052	34	9	web	web	NOUN
fcis-2052	34	10	pages	page	NOUN
fcis-2052	34	11	into	into	ADP
fcis-2052	34	12	plain	plain	ADJ
fcis-2052	34	13	text	text	NOUN
fcis-2052	34	14	format	format	NOUN
fcis-2052	34	15	,	,	PUNCT
fcis-2052	34	16	mark	mark	VERB
fcis-2052	34	17	the	the	DET
fcis-2052	34	18	text	text	NOUN
fcis-2052	34	19	in	in	ADP
fcis-2052	34	20	specific	specific	ADJ
fcis-2052	34	21	labels	label	NOUN
fcis-2052	34	22	,	,	PUNCT
fcis-2052	34	23	and	and	CCONJ
fcis-2052	34	24	store	store	VERB
fcis-2052	34	25	it	it	PRON
fcis-2052	34	26	in	in	ADP
fcis-2052	34	27	the	the	DET
fcis-2052	34	28	"	"	PUNCT
fcis-2052	34	29	text	text	NOUN
fcis-2052	34	30	database	database	NOUN
fcis-2052	34	31	"	"	PUNCT
fcis-2052	34	32	.	.	PUNCT
fcis-2052	35	1	3	3	X
fcis-2052	35	2	)	)	PUNCT
fcis-2052	35	3	text	text	NOUN
fcis-2052	35	4	representation	representation	NOUN
fcis-2052	35	5	:	:	PUNCT
fcis-2052	35	6	refer	refer	VERB
fcis-2052	35	7	to	to	ADP
fcis-2052	35	8	the	the	DET
fcis-2052	35	9	keyword	keyword	NOUN
fcis-2052	35	10	set	set	VERB
fcis-2052	35	11	in	in	ADP
fcis-2052	35	12	the	the	DET
fcis-2052	35	13	"	"	PUNCT
fcis-2052	35	14	user	user	NOUN
fcis-2052	35	15	template	template	NOUN
fcis-2052	35	16	"	"	PUNCT
fcis-2052	35	17	,	,	PUNCT
fcis-2052	35	18	use	use	VERB
fcis-2052	35	19	the	the	DET
fcis-2052	35	20	improved	improved	ADJ
fcis-2052	35	21	algorithm	algorithm	NOUN
fcis-2052	35	22	of	of	ADP
fcis-2052	35	23	web	web	NOUN
fcis-2052	35	24	page	page	NOUN
fcis-2052	35	25	text	text	NOUN
fcis-2052	35	26	representation	representation	NOUN
fcis-2052	35	27	,	,	PUNCT
fcis-2052	35	28	perform	perform	VERB
fcis-2052	35	29	word	word	NOUN
fcis-2052	35	30	segmentation	segmentation	NOUN
fcis-2052	35	31	,	,	PUNCT
fcis-2052	35	32	and	and	CCONJ
fcis-2052	35	33	calculate	calculate	VERB
fcis-2052	35	34	the	the	DET
fcis-2052	35	35	weight	weight	NOUN
fcis-2052	35	36	,	,	PUNCT
fcis-2052	35	37	and	and	CCONJ
fcis-2052	35	38	finally	finally	ADV
fcis-2052	35	39	express	express	VERB
fcis-2052	35	40	the	the	DET
fcis-2052	35	41	document	document	NOUN
fcis-2052	35	42	as	as	ADP
fcis-2052	35	43	a	a	DET
fcis-2052	35	44	vector	vector	NOUN
fcis-2052	35	45	space	space	NOUN
fcis-2052	35	46	model	model	NOUN
fcis-2052	35	47	.	.	PUNCT
fcis-2052	36	1	4	4	X
fcis-2052	36	2	)	)	PUNCT
fcis-2052	36	3	text	text	NOUN
fcis-2052	36	4	matching	matching	NOUN
fcis-2052	36	5	:	:	PUNCT
fcis-2052	36	6	calculate	calculate	VERB
fcis-2052	36	7	the	the	DET
fcis-2052	36	8	similarity	similarity	NOUN
fcis-2052	36	9	between	between	ADP
fcis-2052	36	10	the	the	DET
fcis-2052	36	11	vector	vector	NOUN
fcis-2052	36	12	expression	expression	NOUN
fcis-2052	36	13	obtained	obtain	VERB
fcis-2052	36	14	in	in	ADP
fcis-2052	36	15	the	the	DET
fcis-2052	36	16	"	"	PUNCT
fcis-2052	36	17	text	text	NOUN
fcis-2052	36	18	representation	representation	NOUN
fcis-2052	36	19	"	"	PUNCT
fcis-2052	36	20	and	and	CCONJ
fcis-2052	36	21	the	the	DET
fcis-2052	36	22	vector	vector	NOUN
fcis-2052	36	23	expression	expression	NOUN
fcis-2052	36	24	in	in	ADP
fcis-2052	36	25	the	the	DET
fcis-2052	36	26	"	"	PUNCT
fcis-2052	36	27	user	user	NOUN
fcis-2052	36	28	template	template	NOUN
fcis-2052	36	29	"	"	PUNCT
fcis-2052	36	30	,	,	PUNCT
fcis-2052	36	31	find	find	VERB
fcis-2052	36	32	out	out	ADP
fcis-2052	36	33	the	the	DET
fcis-2052	36	34	documents	document	NOUN
fcis-2052	36	35	with	with	ADP
fcis-2052	36	36	a	a	DET
fcis-2052	36	37	certain	certain	ADJ
fcis-2052	36	38	matching	matching	NOUN
fcis-2052	36	39	relationship	relationship	NOUN
fcis-2052	36	40	(	(	PUNCT
fcis-2052	36	41	that	that	ADV
fcis-2052	36	42	is	is	ADV
fcis-2052	36	43	,	,	PUNCT
fcis-2052	36	44	the	the	DET
fcis-2052	36	45	web	web	NOUN
fcis-2052	36	46	pages	page	NOUN
fcis-2052	36	47	to	to	PART
fcis-2052	36	48	be	be	AUX
fcis-2052	36	49	filtered	filter	VERB
fcis-2052	36	50	)	)	PUNCT
fcis-2052	36	51	,	,	PUNCT
fcis-2052	36	52	and	and	CCONJ
fcis-2052	36	53	mark	mark	VERB
fcis-2052	36	54	the	the	DET
fcis-2052	36	55	evaluation	evaluation	NOUN
fcis-2052	36	56	results	result	NOUN
fcis-2052	36	57	of	of	ADP
fcis-2052	36	58	the	the	DET
fcis-2052	36	59	system	system	NOUN
fcis-2052	36	60	.	.	PUNCT
fcis-2052	37	1	5	5	X
fcis-2052	37	2	)	)	PUNCT
fcis-2052	37	3	text	text	NOUN
fcis-2052	37	4	filtering	filtering	NOUN
fcis-2052	37	5	:	:	PUNCT
fcis-2052	37	6	submit	submit	VERB
fcis-2052	37	7	users	user	NOUN
fcis-2052	37	8	'	'	PART
fcis-2052	37	9	filtering	filtering	NOUN
fcis-2052	37	10	requests	request	NOUN
fcis-2052	37	11	and	and	CCONJ
fcis-2052	37	12	deliver	deliver	VERB
fcis-2052	37	13	the	the	DET
fcis-2052	37	14	evaluation	evaluation	NOUN
fcis-2052	37	15	results	result	NOUN
fcis-2052	37	16	of	of	ADP
fcis-2052	37	17	the	the	DET
fcis-2052	37	18	system	system	NOUN
fcis-2052	37	19	.	.	PUNCT
fcis-2052	38	1	6)template	6)template	NUM
fcis-2052	38	2	management	management	NOUN
fcis-2052	38	3	:	:	PUNCT
fcis-2052	38	4	according	accord	VERB
fcis-2052	38	5	to	to	ADP
fcis-2052	38	6	the	the	DET
fcis-2052	38	7	learning	learning	NOUN
fcis-2052	38	8	mechanism	mechanism	NOUN
fcis-2052	38	9	of	of	ADP
fcis-2052	38	10	user	user	NOUN
fcis-2052	38	11	templates	template	NOUN
fcis-2052	38	12	customized	customize	VERB
fcis-2052	38	13	by	by	ADP
fcis-2052	38	14	users	user	NOUN
fcis-2052	38	15	,	,	PUNCT
fcis-2052	38	16	a	a	DET
fcis-2052	38	17	certain	certain	ADJ
fcis-2052	38	18	number	number	NOUN
fcis-2052	38	19	of	of	ADP
fcis-2052	38	20	pages	page	NOUN
fcis-2052	38	21	from	from	ADP
fcis-2052	38	22	the	the	DET
fcis-2052	38	23	"	"	PUNCT
fcis-2052	38	24	url	url	NOUN
fcis-2052	38	25	database	database	NOUN
fcis-2052	38	26	"	"	PUNCT
fcis-2052	38	27	will	will	AUX
fcis-2052	38	28	be	be	AUX
fcis-2052	38	29	added	add	VERB
fcis-2052	38	30	to	to	ADP
fcis-2052	38	31	the	the	DET
fcis-2052	38	32	training	training	NOUN
fcis-2052	38	33	set	set	NOUN
fcis-2052	38	34	,	,	PUNCT
fcis-2052	38	35	and	and	CCONJ
fcis-2052	38	36	the	the	DET
fcis-2052	38	37	genetic	genetic	ADJ
fcis-2052	38	38	algorithm	algorithm	NOUN
fcis-2052	38	39	will	will	AUX
fcis-2052	38	40	be	be	AUX
fcis-2052	38	41	used	use	VERB
fcis-2052	38	42	for	for	ADP
fcis-2052	38	43	self	self	NOUN
fcis-2052	38	44	-	-	PUNCT
fcis-2052	38	45	learning	learn	VERB
fcis-2052	38	46	and	and	CCONJ
fcis-2052	38	47	inductive	inductive	ADJ
fcis-2052	38	48	update	update	NOUN
fcis-2052	38	49	to	to	PART
fcis-2052	38	50	improve	improve	VERB
fcis-2052	38	51	the	the	DET
fcis-2052	38	52	"	"	PUNCT
fcis-2052	38	53	user	user	NOUN
fcis-2052	38	54	template	template	NOUN
fcis-2052	38	55	"	"	PUNCT
fcis-2052	38	56	,	,	PUNCT
fcis-2052	38	57	so	so	SCONJ
fcis-2052	38	58	as	as	SCONJ
fcis-2052	38	59	to	to	PART
fcis-2052	38	60	ensure	ensure	VERB
fcis-2052	38	61	the	the	DET
fcis-2052	38	62	filtering	filter	VERB
fcis-2052	38	63	performance	performance	NOUN
fcis-2052	38	64	of	of	ADP
fcis-2052	38	65	the	the	DET
fcis-2052	38	66	system	system	NOUN
fcis-2052	38	67	.	.	PUNCT
fcis-2052	39	1	7)thesaurus	7)thesaurus	NUM
fcis-2052	39	2	management	management	NOUN
fcis-2052	39	3	:	:	PUNCT
fcis-2052	39	4	complete	complete	VERB
fcis-2052	39	5	the	the	DET
fcis-2052	39	6	dictionary	dictionary	ADJ
fcis-2052	39	7	improvement	improvement	NOUN
fcis-2052	39	8	function	function	NOUN
fcis-2052	39	9	.	.	PUNCT
fcis-2052	40	1	the	the	DET
fcis-2052	40	2	user	user	NOUN
fcis-2052	40	3	interface	interface	NOUN
fcis-2052	40	4	provides	provide	VERB
fcis-2052	40	5	a	a	DET
fcis-2052	40	6	management	management	NOUN
fcis-2052	40	7	interface	interface	NOUN
fcis-2052	40	8	.	.	PUNCT
fcis-2052	41	1	you	you	PRON
fcis-2052	41	2	can	can	AUX
fcis-2052	41	3	preview	preview	VERB
fcis-2052	41	4	the	the	DET
fcis-2052	41	5	word	word	NOUN
fcis-2052	41	6	segmentation	segmentation	NOUN
fcis-2052	41	7	results	result	NOUN
fcis-2052	41	8	of	of	ADP
fcis-2052	41	9	a	a	DET
fcis-2052	41	10	document	document	NOUN
fcis-2052	41	11	,	,	PUNCT
fcis-2052	41	12	view	view	VERB
fcis-2052	41	13	the	the	DET
fcis-2052	41	14	reasonable	reasonable	ADJ
fcis-2052	41	15	and	and	CCONJ
fcis-2052	41	16	unreasonable	unreasonable	ADJ
fcis-2052	41	17	words	word	NOUN
fcis-2052	41	18	in	in	ADP
fcis-2052	41	19	the	the	DET
fcis-2052	41	20	dictionary	dictionary	ADJ
fcis-2052	41	21	database	database	NOUN
fcis-2052	41	22	and	and	CCONJ
fcis-2052	41	23	the	the	DET
fcis-2052	41	24	stop	stop	NOUN
fcis-2052	41	25	word	word	NOUN
fcis-2052	41	26	database	database	NOUN
fcis-2052	41	27	,	,	PUNCT
fcis-2052	41	28	optimize	optimize	VERB
fcis-2052	41	29	the	the	DET
fcis-2052	41	30	"	"	PUNCT
fcis-2052	41	31	dictionary	dictionary	ADJ
fcis-2052	41	32	database	database	NOUN
fcis-2052	41	33	"	"	PUNCT
fcis-2052	41	34	,	,	PUNCT
fcis-2052	41	35	and	and	CCONJ
fcis-2052	41	36	the	the	DET
fcis-2052	41	37	word	word	NOUN
fcis-2052	41	38	segmentation	segmentation	NOUN
fcis-2052	41	39	results	result	NOUN
fcis-2052	41	40	will	will	AUX
fcis-2052	41	41	be	be	AUX
fcis-2052	41	42	more	more	ADV
fcis-2052	41	43	accurate	accurate	ADJ
fcis-2052	41	44	.	.	PUNCT
fcis-2052	42	1	8)	8)	NUM
fcis-2052	42	2	url	url	NOUN
fcis-2052	42	3	management	management	NOUN
fcis-2052	42	4	:	:	PUNCT
fcis-2052	42	5	complete	complete	ADJ
fcis-2052	42	6	user	user	NOUN
fcis-2052	42	7	feedback	feedback	NOUN
fcis-2052	42	8	of	of	ADP
fcis-2052	42	9	system	system	NOUN
fcis-2052	42	10	evaluation	evaluation	NOUN
fcis-2052	42	11	results	result	NOUN
fcis-2052	43	1	and	and	CCONJ
fcis-2052	43	2	get	get	VERB
fcis-2052	43	3	the	the	DET
fcis-2052	43	4	final	final	ADJ
fcis-2052	43	5	results	result	NOUN
fcis-2052	43	6	.	.	PUNCT
fcis-2052	44	1	the	the	DET
fcis-2052	44	2	user	user	NOUN
fcis-2052	44	3	interface	interface	NOUN
fcis-2052	44	4	provides	provide	VERB
fcis-2052	44	5	an	an	DET
fcis-2052	44	6	interface	interface	NOUN
fcis-2052	44	7	to	to	PART
fcis-2052	44	8	view	view	VERB
fcis-2052	44	9	and	and	CCONJ
fcis-2052	44	10	browse	browse	VERB
fcis-2052	44	11	the	the	DET
fcis-2052	44	12	page	page	NOUN
fcis-2052	44	13	of	of	ADP
fcis-2052	44	14	the	the	DET
fcis-2052	44	15	existing	exist	VERB
fcis-2052	44	16	system	system	NOUN
fcis-2052	44	17	evaluation	evaluation	NOUN
fcis-2052	44	18	,	,	PUNCT
fcis-2052	44	19	give	give	VERB
fcis-2052	44	20	a	a	DET
fcis-2052	44	21	manual	manual	ADJ
fcis-2052	44	22	evaluation	evaluation	NOUN
fcis-2052	44	23	,	,	PUNCT
fcis-2052	44	24	and	and	CCONJ
fcis-2052	44	25	record	record	VERB
fcis-2052	44	26	it	it	PRON
fcis-2052	44	27	in	in	ADP
fcis-2052	44	28	the	the	DET
fcis-2052	44	29	url	url	NOUN
fcis-2052	44	30	database	database	NOUN
fcis-2052	44	31	.	.	PUNCT
fcis-2052	45	1	in	in	ADP
fcis-2052	45	2	addition	addition	NOUN
fcis-2052	45	3	,	,	PUNCT
fcis-2052	45	4	in	in	ADP
fcis-2052	45	5	view	view	NOUN
fcis-2052	45	6	of	of	ADP
fcis-2052	45	7	the	the	DET
fcis-2052	45	8	network	network	NOUN
fcis-2052	45	9	information	information	NOUN
fcis-2052	45	10	change	change	NOUN
fcis-2052	45	11	fast	fast	ADV
fcis-2052	45	12	,	,	PUNCT
fcis-2052	45	13	poor	poor	ADJ
fcis-2052	45	14	stability	stability	NOUN
fcis-2052	45	15	,	,	PUNCT
fcis-2052	45	16	short	short	ADJ
fcis-2052	45	17	web	web	NOUN
fcis-2052	45	18	page	page	NOUN
fcis-2052	45	19	survival	survival	NOUN
fcis-2052	45	20	characteristics	characteristic	NOUN
fcis-2052	45	21	,	,	PUNCT
fcis-2052	45	22	the	the	DET
fcis-2052	45	23	"	"	PUNCT
fcis-2052	45	24	url	url	X
fcis-2052	45	25	database	database	NOUN
fcis-2052	45	26	"	"	PUNCT
fcis-2052	45	27	data	datum	NOUN
fcis-2052	45	28	set	set	VERB
fcis-2052	45	29	time	time	NOUN
fcis-2052	45	30	limit	limit	NOUN
fcis-2052	45	31	,	,	PUNCT
fcis-2052	45	32	from	from	ADP
fcis-2052	45	33	the	the	DET
fcis-2052	45	34	time	time	NOUN
fcis-2052	45	35	of	of	ADP
fcis-2052	45	36	entry	entry	NOUN
fcis-2052	45	37	into	into	ADP
fcis-2052	45	38	the	the	DET
fcis-2052	45	39	database	database	NOUN
fcis-2052	45	40	,	,	PUNCT
fcis-2052	45	41	beyond	beyond	ADP
fcis-2052	45	42	the	the	DET
fcis-2052	45	43	time	time	NOUN
fcis-2052	45	44	limit	limit	NOUN
fcis-2052	45	45	of	of	ADP
fcis-2052	45	46	the	the	DET
fcis-2052	45	47	data	datum	NOUN
fcis-2052	45	48	will	will	AUX
fcis-2052	45	49	automatically	automatically	ADV
fcis-2052	45	50	be	be	AUX
fcis-2052	45	51	removed	remove	VERB
fcis-2052	45	52	from	from	ADP
fcis-2052	45	53	the	the	DET
fcis-2052	45	54	database	database	NOUN
fcis-2052	45	55	.	.	PUNCT
fcis-2052	46	1	the	the	DET
fcis-2052	46	2	"	"	PUNCT
fcis-2052	46	3	text	text	NOUN
fcis-2052	46	4	database	database	NOUN
fcis-2052	46	5	"	"	PUNCT
fcis-2052	46	6	stores	store	NOUN
fcis-2052	46	7	the	the	DET
fcis-2052	46	8	text	text	NOUN
fcis-2052	46	9	data	datum	NOUN
fcis-2052	46	10	and	and	CCONJ
fcis-2052	46	11	related	related	ADJ
fcis-2052	46	12	attributes	attribute	NOUN
fcis-2052	46	13	of	of	ADP
fcis-2052	46	14	all	all	DET
fcis-2052	46	15	intercepted	intercept	VERB
fcis-2052	46	16	web	web	NOUN
fcis-2052	46	17	pages	page	NOUN
fcis-2052	46	18	,	,	PUNCT
fcis-2052	46	19	and	and	CCONJ
fcis-2052	46	20	the	the	DET
fcis-2052	46	21	"	"	PUNCT
fcis-2052	46	22	url	url	X
fcis-2052	46	23	database	database	NOUN
fcis-2052	46	24	"	"	PUNCT
fcis-2052	46	25	records	record	VERB
fcis-2052	46	26	the	the	DET
fcis-2052	46	27	url	url	PROPN
fcis-2052	46	28	link	link	NOUN
fcis-2052	46	29	addresses	address	NOUN
fcis-2052	46	30	and	and	CCONJ
fcis-2052	46	31	related	related	ADJ
fcis-2052	46	32	attributes	attribute	NOUN
fcis-2052	46	33	of	of	ADP
fcis-2052	46	34	the	the	DET
fcis-2052	46	35	pages	page	NOUN
fcis-2052	46	36	that	that	PRON
fcis-2052	46	37	are	be	AUX
fcis-2052	46	38	rated	rate	VERB
fcis-2052	46	39	to	to	PART
fcis-2052	46	40	be	be	AUX
fcis-2052	46	41	filtered	filter	VERB
fcis-2052	46	42	.	.	PUNCT
fcis-2052	47	1	3	3	X
fcis-2052	47	2	.	.	X
fcis-2052	47	3	analysis	analysis	NOUN
fcis-2052	47	4	of	of	ADP
fcis-2052	47	5	key	key	ADJ
fcis-2052	47	6	technologies	technology	NOUN
fcis-2052	47	7	the	the	DET
fcis-2052	47	8	web	web	NOUN
fcis-2052	47	9	page	page	NOUN
fcis-2052	47	10	bad	bad	ADJ
fcis-2052	47	11	information	information	NOUN
fcis-2052	47	12	filtering	filter	VERB
fcis-2052	47	13	system	system	NOUN
fcis-2052	47	14	is	be	AUX
fcis-2052	47	15	divided	divide	VERB
fcis-2052	47	16	into	into	ADP
fcis-2052	47	17	three	three	NUM
fcis-2052	47	18	functional	functional	ADJ
fcis-2052	47	19	modules	module	NOUN
fcis-2052	47	20	:	:	PUNCT
fcis-2052	47	21	network	network	NOUN
fcis-2052	47	22	data	datum	NOUN
fcis-2052	47	23	processing	processing	NOUN
fcis-2052	47	24	,	,	PUNCT
fcis-2052	47	25	text	text	NOUN
fcis-2052	47	26	data	datum	NOUN
fcis-2052	47	27	processing	processing	NOUN
fcis-2052	47	28	and	and	CCONJ
fcis-2052	47	29	adaptive	adaptive	ADJ
fcis-2052	47	30	processing	processing	NOUN
fcis-2052	47	31	.	.	PUNCT
fcis-2052	48	1	network	network	NOUN
fcis-2052	48	2	data	datum	NOUN
fcis-2052	48	3	processing	processing	NOUN
fcis-2052	48	4	:	:	PUNCT
fcis-2052	48	5	winpcap	winpcap	NOUN
fcis-2052	48	6	,	,	PUNCT
fcis-2052	48	7	a	a	DET
fcis-2052	48	8	network	network	NOUN
fcis-2052	48	9	packet	packet	NOUN
fcis-2052	48	10	capture	capture	NOUN
fcis-2052	48	11	library	library	NOUN
fcis-2052	48	12	under	under	ADP
fcis-2052	48	13	windows	window	NOUN
fcis-2052	48	14	platform	platform	NOUN
fcis-2052	48	15	,	,	PUNCT
fcis-2052	48	16	is	be	AUX
fcis-2052	48	17	used	use	VERB
fcis-2052	48	18	to	to	PART
fcis-2052	48	19	capture	capture	VERB
fcis-2052	48	20	network	network	NOUN
fcis-2052	48	21	data	datum	NOUN
fcis-2052	48	22	by	by	ADP
fcis-2052	48	23	setting	set	VERB
fcis-2052	48	24	the	the	DET
fcis-2052	48	25	network	network	NOUN
fcis-2052	48	26	card	card	NOUN
fcis-2052	48	27	to	to	ADP
fcis-2052	48	28	a	a	DET
fcis-2052	48	29	hybrid	hybrid	ADJ
fcis-2052	48	30	mode	mode	NOUN
fcis-2052	48	31	;	;	PUNCT
fcis-2052	48	32	network	network	NOUN
fcis-2052	48	33	data	datum	NOUN
fcis-2052	48	34	analysis	analysis	NOUN
fcis-2052	48	35	is	be	AUX
fcis-2052	48	36	another	another	DET
fcis-2052	48	37	key	key	ADJ
fcis-2052	48	38	technology	technology	NOUN
fcis-2052	48	39	of	of	ADP
fcis-2052	48	40	network	network	NOUN
fcis-2052	48	41	data	datum	NOUN
fcis-2052	48	42	processing	processing	NOUN
fcis-2052	48	43	.	.	PUNCT
fcis-2052	49	1	in	in	ADP
fcis-2052	49	2	the	the	DET
fcis-2052	49	3	process	process	NOUN
fcis-2052	49	4	of	of	ADP
fcis-2052	49	5	analysis	analysis	NOUN
fcis-2052	49	6	,	,	PUNCT
fcis-2052	49	7	network	network	NOUN
fcis-2052	49	8	protocol	protocol	NOUN
fcis-2052	49	9	formats	format	NOUN
fcis-2052	49	10	are	be	AUX
fcis-2052	49	11	ethernet	ethernet	NOUN
fcis-2052	49	12	data	datum	NOUN
fcis-2052	49	13	frame	frame	NOUN
fcis-2052	49	14	,	,	PUNCT
fcis-2052	49	15	ip	ip	PROPN
fcis-2052	49	16	protocol	protocol	NOUN
fcis-2052	49	17	,	,	PUNCT
fcis-2052	49	18	tcp	tcp	INTJ
fcis-2052	49	19	protocol	protocol	NOUN
fcis-2052	49	20	and	and	CCONJ
fcis-2052	49	21	http	http	PROPN
fcis-2052	49	22	message	message	NOUN
fcis-2052	49	23	.	.	PUNCT
fcis-2052	50	1	html	html	NOUN
fcis-2052	50	2	page	page	NOUN
fcis-2052	50	3	reorganization	reorganization	NOUN
fcis-2052	50	4	is	be	AUX
fcis-2052	50	5	also	also	ADV
fcis-2052	50	6	a	a	DET
fcis-2052	50	7	very	very	ADV
fcis-2052	50	8	important	important	ADJ
fcis-2052	50	9	technology	technology	NOUN
fcis-2052	50	10	in	in	ADP
fcis-2052	50	11	web	web	NOUN
fcis-2052	50	12	data	datum	NOUN
fcis-2052	50	13	.	.	PUNCT
fcis-2052	51	1	text	text	NOUN
fcis-2052	51	2	data	datum	NOUN
fcis-2052	51	3	processing	processing	NOUN
fcis-2052	51	4	involves	involve	VERB
fcis-2052	51	5	two	two	NUM
fcis-2052	51	6	important	important	ADJ
fcis-2052	51	7	techniques	technique	NOUN
fcis-2052	51	8	.	.	PUNCT
fcis-2052	52	1	the	the	DET
fcis-2052	52	2	first	first	ADJ
fcis-2052	52	3	is	be	AUX
fcis-2052	52	4	chinese	chinese	ADJ
fcis-2052	52	5	word	word	NOUN
fcis-2052	52	6	segmentation	segmentation	NOUN
fcis-2052	52	7	technology	technology	NOUN
fcis-2052	52	8	:	:	PUNCT
fcis-2052	52	9	for	for	ADP
fcis-2052	52	10	the	the	DET
fcis-2052	52	11	processing	processing	NOUN
fcis-2052	52	12	of	of	ADP
fcis-2052	52	13	chinese	chinese	ADJ
fcis-2052	52	14	word	word	NOUN
fcis-2052	52	15	segmentation	segmentation	NOUN
fcis-2052	52	16	,	,	PUNCT
fcis-2052	52	17	the	the	DET
fcis-2052	52	18	web	web	NOUN
fcis-2052	52	19	page	page	NOUN
fcis-2052	52	20	bad	bad	ADJ
fcis-2052	52	21	information	information	NOUN
fcis-2052	52	22	filtering	filter	VERB
fcis-2052	52	23	system	system	NOUN
fcis-2052	52	24	adopts	adopt	VERB
fcis-2052	52	25	some	some	DET
fcis-2052	52	26	chinese	chinese	ADJ
fcis-2052	52	27	word	word	NOUN
fcis-2052	52	28	segmentation	segmentation	NOUN
fcis-2052	52	29	algorithms	algorithm	NOUN
fcis-2052	52	30	combined	combine	VERB
fcis-2052	52	31	with	with	ADP
fcis-2052	52	32	dictionary	dictionary	ADJ
fcis-2052	52	33	database	database	NOUN
fcis-2052	52	34	.	.	PUNCT
fcis-2052	53	1	first	first	ADV
fcis-2052	53	2	,	,	PUNCT
fcis-2052	53	3	the	the	DET
fcis-2052	53	4	forward	forward	ADJ
fcis-2052	53	5	maximum	maximum	ADJ
fcis-2052	53	6	matching	matching	NOUN
fcis-2052	53	7	method	method	NOUN
fcis-2052	53	8	and	and	CCONJ
fcis-2052	53	9	the	the	DET
fcis-2052	53	10	reverse	reverse	ADJ
fcis-2052	53	11	maximum	maximum	ADJ
fcis-2052	53	12	matching	matching	NOUN
fcis-2052	53	13	method	method	NOUN
fcis-2052	53	14	are	be	AUX
fcis-2052	53	15	used	use	VERB
fcis-2052	53	16	for	for	ADP
fcis-2052	53	17	word	word	NOUN
fcis-2052	53	18	segmentation	segmentation	NOUN
fcis-2052	53	19	,	,	PUNCT
fcis-2052	53	20	and	and	CCONJ
fcis-2052	53	21	the	the	DET
fcis-2052	53	22	results	result	NOUN
fcis-2052	53	23	are	be	AUX
fcis-2052	53	24	compared	compare	VERB
fcis-2052	53	25	.	.	PUNCT
fcis-2052	54	1	if	if	SCONJ
fcis-2052	54	2	there	there	PRON
fcis-2052	54	3	are	be	VERB
fcis-2052	54	4	different	different	ADJ
fcis-2052	54	5	,	,	PUNCT
fcis-2052	54	6	the	the	DET
fcis-2052	54	7	results	result	NOUN
fcis-2052	54	8	are	be	AUX
fcis-2052	54	9	selected	select	VERB
fcis-2052	54	10	by	by	ADP
fcis-2052	54	11	the	the	DET
fcis-2052	54	12	maximum	maximum	ADJ
fcis-2052	54	13	probability	probability	NOUN
fcis-2052	54	14	method	method	NOUN
fcis-2052	54	15	.	.	PUNCT
fcis-2052	55	1	the	the	DET
fcis-2052	55	2	word	word	NOUN
fcis-2052	55	3	segmentation	segmentation	NOUN
fcis-2052	55	4	process	process	NOUN
fcis-2052	55	5	is	be	AUX
fcis-2052	55	6	shown	show	VERB
fcis-2052	55	7	in	in	ADP
fcis-2052	55	8	figure	figure	NOUN
fcis-2052	55	9	2	2	NUM
fcis-2052	55	10	:	:	PUNCT
fcis-2052	55	11	figure	figure	NOUN
fcis-2052	55	12	2	2	NUM
fcis-2052	55	13	.	.	PUNCT
fcis-2052	55	14	word	word	NOUN
fcis-2052	55	15	segmentation	segmentation	NOUN
fcis-2052	55	16	process	process	NOUN
fcis-2052	55	17	the	the	DET
fcis-2052	55	18	second	second	NOUN
fcis-2052	55	19	is	be	AUX
fcis-2052	55	20	text	text	NOUN
fcis-2052	55	21	representation	representation	NOUN
fcis-2052	55	22	technology	technology	NOUN
fcis-2052	55	23	:	:	PUNCT
fcis-2052	55	24	firstly	firstly	ADV
fcis-2052	55	25	,	,	PUNCT
fcis-2052	55	26	extract	extract	VERB
fcis-2052	55	27	feature	feature	NOUN
fcis-2052	55	28	items	item	NOUN
fcis-2052	55	29	from	from	ADP
fcis-2052	55	30	documents	document	NOUN
fcis-2052	55	31	by	by	ADP
fcis-2052	55	32	referring	refer	VERB
fcis-2052	55	33	to	to	ADP
fcis-2052	55	34	user	user	NOUN
fcis-2052	55	35	templates	template	NOUN
fcis-2052	55	36	.	.	PUNCT
fcis-2052	56	1	in	in	ADP
fcis-2052	56	2	this	this	DET
fcis-2052	56	3	paper	paper	NOUN
fcis-2052	56	4	,	,	PUNCT
fcis-2052	56	5	an	an	DET
fcis-2052	56	6	improved	improved	ADJ
fcis-2052	56	7	algorithm	algorithm	NOUN
fcis-2052	56	8	for	for	ADP
fcis-2052	56	9	web	web	NOUN
fcis-2052	56	10	page	page	NOUN
fcis-2052	56	11	text	text	NOUN
fcis-2052	56	12	representation	representation	NOUN
fcis-2052	56	13	is	be	AUX
fcis-2052	56	14	proposed	propose	VERB
fcis-2052	56	15	,	,	PUNCT
fcis-2052	56	16	which	which	PRON
fcis-2052	56	17	extracts	extract	VERB
fcis-2052	56	18	feature	feature	NOUN
fcis-2052	56	19	items	item	NOUN
fcis-2052	56	20	from	from	ADP
fcis-2052	56	21	web	web	NOUN
fcis-2052	56	22	pages	page	NOUN
fcis-2052	56	23	.	.	PUNCT
fcis-2052	57	1	this	this	DET
fcis-2052	57	2	method	method	NOUN
fcis-2052	57	3	is	be	AUX
fcis-2052	57	4	accurate	accurate	ADJ
fcis-2052	57	5	and	and	CCONJ
fcis-2052	57	6	fast	fast	ADJ
fcis-2052	57	7	,	,	PUNCT
fcis-2052	57	8	and	and	CCONJ
fcis-2052	57	9	can	can	AUX
fcis-2052	57	10	ensure	ensure	VERB
fcis-2052	57	11	the	the	DET
fcis-2052	57	12	real	real	ADJ
fcis-2052	57	13	-	-	PUNCT
fcis-2052	57	14	time	time	NOUN
fcis-2052	57	15	performance	performance	NOUN
fcis-2052	57	16	of	of	ADP
fcis-2052	57	17	web	web	NOUN
fcis-2052	57	18	page	page	NOUN
fcis-2052	57	19	filtering	filtering	NOUN
fcis-2052	57	20	.	.	PUNCT
fcis-2052	58	1	then	then	ADV
fcis-2052	58	2	calculate	calculate	VERB
fcis-2052	58	3	the	the	DET
fcis-2052	58	4	weight	weight	NOUN
fcis-2052	58	5	of	of	ADP
fcis-2052	58	6	the	the	DET
fcis-2052	58	7	keyword	keyword	NOUN
fcis-2052	58	8	,	,	PUNCT
fcis-2052	58	9	and	and	CCONJ
fcis-2052	58	10	use	use	VERB
fcis-2052	58	11	the	the	DET
fcis-2052	58	12	vector	vector	NOUN
fcis-2052	58	13	space	space	NOUN
fcis-2052	58	14	model	model	NOUN
fcis-2052	58	15	to	to	PART
fcis-2052	58	16	represent	represent	VERB
fcis-2052	58	17	the	the	DET
fcis-2052	58	18	document	document	NOUN
fcis-2052	58	19	.	.	PUNCT
fcis-2052	59	1	finally	finally	ADV
fcis-2052	59	2	,	,	PUNCT
fcis-2052	59	3	the	the	DET
fcis-2052	59	4	angle	angle	NOUN
fcis-2052	59	5	between	between	ADP
fcis-2052	59	6	the	the	DET
fcis-2052	59	7	user	user	NOUN
fcis-2052	59	8	template	template	NOUN
fcis-2052	59	9	vector	vector	NOUN
fcis-2052	59	10	and	and	CCONJ
fcis-2052	59	11	the	the	DET
fcis-2052	59	12	document	document	NOUN
fcis-2052	59	13	vector	vector	NOUN
fcis-2052	59	14	is	be	AUX
fcis-2052	59	15	calculated	calculate	VERB
fcis-2052	59	16	to	to	PART
fcis-2052	59	17	determine	determine	VERB
fcis-2052	59	18	the	the	DET
fcis-2052	59	19	similarity	similarity	NOUN
fcis-2052	59	20	.	.	PUNCT
fcis-2052	60	1	the	the	DET
fcis-2052	60	2	similarity	similarity	NOUN
fcis-2052	60	3	is	be	AUX
fcis-2052	60	4	compared	compare	VERB
fcis-2052	60	5	with	with	ADP
fcis-2052	60	6	a	a	DET
fcis-2052	60	7	certain	certain	ADJ
fcis-2052	60	8	threshold	threshold	NOUN
fcis-2052	60	9	to	to	PART
fcis-2052	60	10	determine	determine	VERB
fcis-2052	60	11	the	the	DET
fcis-2052	60	12	ownership	ownership	NOUN
fcis-2052	60	13	of	of	ADP
fcis-2052	60	14	the	the	DET
fcis-2052	60	15	document	document	NOUN
fcis-2052	60	16	.	.	PUNCT
fcis-2052	61	1	the	the	DET
fcis-2052	61	2	establishment	establishment	NOUN
fcis-2052	61	3	of	of	ADP
fcis-2052	61	4	the	the	DET
fcis-2052	61	5	initial	initial	ADJ
fcis-2052	61	6	user	user	NOUN
fcis-2052	61	7	template	template	NOUN
fcis-2052	61	8	is	be	AUX
fcis-2052	61	9	also	also	ADV
fcis-2052	61	10	a	a	DET
fcis-2052	61	11	key	key	ADJ
fcis-2052	61	12	technology	technology	NOUN
fcis-2052	61	13	in	in	ADP
fcis-2052	61	14	text	text	NOUN
fcis-2052	61	15	representation	representation	NOUN
fcis-2052	61	16	.	.	PUNCT
fcis-2052	62	1	the	the	DET
fcis-2052	62	2	filtering	filter	VERB
fcis-2052	62	3	system	system	NOUN
fcis-2052	62	4	uses	use	VERB
fcis-2052	62	5	the	the	DET
fcis-2052	62	6	vector	vector	NOUN
fcis-2052	62	7	space	space	NOUN
fcis-2052	62	8	model	model	NOUN
fcis-2052	62	9	to	to	PART
fcis-2052	62	10	represent	represent	VERB
fcis-2052	62	11	the	the	DET
fcis-2052	62	12	initial	initial	ADJ
fcis-2052	62	13	user	user	NOUN
fcis-2052	62	14	template	template	NOUN
fcis-2052	62	15	by	by	ADP
fcis-2052	62	16	segmentation	segmentation	NOUN
fcis-2052	62	17	of	of	ADP
fcis-2052	62	18	the	the	DET
fcis-2052	62	19	training	training	NOUN
fcis-2052	62	20	document	document	NOUN
fcis-2052	62	21	and	and	CCONJ
fcis-2052	62	22	counting	count	VERB
fcis-2052	62	23	the	the	DET
fcis-2052	62	24	word	word	NOUN
fcis-2052	62	25	frequency	frequency	NOUN
fcis-2052	62	26	.	.	PUNCT
fcis-2052	63	1	the	the	DET
fcis-2052	63	2	adaptive	adaptive	ADJ
fcis-2052	63	3	processing	processing	NOUN
fcis-2052	63	4	part	part	NOUN
fcis-2052	63	5	is	be	AUX
fcis-2052	63	6	achieved	achieve	VERB
fcis-2052	63	7	through	through	ADP
fcis-2052	63	8	user	user	NOUN
fcis-2052	63	9	feedback	feedback	NOUN
fcis-2052	63	10	and	and	CCONJ
fcis-2052	63	11	machine	machine	NOUN
fcis-2052	63	12	learning	learning	NOUN
fcis-2052	63	13	.	.	PUNCT
fcis-2052	64	1	the	the	DET
fcis-2052	64	2	web	web	NOUN
fcis-2052	64	3	page	page	NOUN
fcis-2052	64	4	bad	bad	ADJ
fcis-2052	64	5	information	information	NOUN
fcis-2052	64	6	filtering	filter	VERB
fcis-2052	64	7	system	system	NOUN
fcis-2052	64	8	designed	design	VERB
fcis-2052	64	9	a	a	DET
fcis-2052	64	10	human	human	ADJ
fcis-2052	64	11	-	-	PUNCT
fcis-2052	64	12	computer	computer	NOUN
fcis-2052	64	13	interaction	interaction	NOUN
fcis-2052	64	14	interface	interface	NOUN
fcis-2052	64	15	for	for	ADP
fcis-2052	64	16	various	various	ADJ
fcis-2052	64	17	information	information	NOUN
fcis-2052	64	18	feedback	feedback	NOUN
fcis-2052	64	19	,	,	PUNCT
fcis-2052	64	20	such	such	ADJ
fcis-2052	64	21	as	as	ADP
fcis-2052	64	22	word	word	NOUN
fcis-2052	64	23	segmentation	segmentation	NOUN
fcis-2052	64	24	preview	preview	NOUN
fcis-2052	64	25	,	,	PUNCT
fcis-2052	64	26	keyword	keyword	NOUN
fcis-2052	64	27	preview	preview	NOUN
fcis-2052	64	28	,	,	PUNCT
fcis-2052	64	29	sensitive	sensitive	ADJ
fcis-2052	64	30	data	datum	NOUN
fcis-2052	64	31	(	(	PUNCT
fcis-2052	64	32	that	that	PRON
fcis-2052	64	33	is	is	ADV
fcis-2052	64	34	,	,	PUNCT
fcis-2052	64	35	the	the	DET
fcis-2052	64	36	system	system	NOUN
fcis-2052	64	37	for	for	ADP
fcis-2052	64	38	the	the	DET
fcis-2052	64	39	first	first	ADJ
fcis-2052	64	40	time	time	NOUN
fcis-2052	64	41	judged	judge	VERB
fcis-2052	64	42	to	to	PART
fcis-2052	64	43	be	be	AUX
fcis-2052	64	44	filtered	filter	VERB
fcis-2052	64	45	by	by	ADP
fcis-2052	64	46	the	the	DET
fcis-2052	64	47	web	web	NOUN
fcis-2052	64	48	page	page	NOUN
fcis-2052	64	49	)	)	PUNCT
fcis-2052	64	50	preview	preview	NOUN
fcis-2052	64	51	,	,	PUNCT
fcis-2052	64	52	and	and	CCONJ
fcis-2052	64	53	providesan	providesan	ADJ
fcis-2052	64	54	interactive	interactive	ADJ
fcis-2052	64	55	interface	interface	NOUN
fcis-2052	64	56	for	for	SCONJ
fcis-2052	64	57	users	user	NOUN
fcis-2052	64	58	to	to	PART
fcis-2052	64	59	maintain	maintain	VERB
fcis-2052	64	60	dictionary	dictionary	ADJ
fcis-2052	64	61	databases	database	NOUN
fcis-2052	64	62	,	,	PUNCT
fcis-2052	64	63	stop	stop	VERB
fcis-2052	64	64	words	word	NOUN
fcis-2052	64	65	databases	database	NOUN
fcis-2052	64	66	,	,	PUNCT
fcis-2052	64	67	sensitive	sensitive	ADJ
fcis-2052	64	68	data	datum	NOUN
fcis-2052	64	69	,	,	PUNCT
fcis-2052	64	70	etc	etc	X
fcis-2052	64	71	.	.	X
fcis-2052	65	1	the	the	DET
fcis-2052	65	2	core	core	NOUN
fcis-2052	65	3	problem	problem	NOUN
fcis-2052	65	4	to	to	PART
fcis-2052	65	5	be	be	AUX
fcis-2052	65	6	solved	solve	VERB
fcis-2052	65	7	by	by	ADP
fcis-2052	65	8	any	any	DET
fcis-2052	65	9	filtering	filter	VERB
fcis-2052	65	10	system	system	NOUN
fcis-2052	65	11	is	be	AUX
fcis-2052	65	12	the	the	DET
fcis-2052	65	13	improvement	improvement	NOUN
fcis-2052	65	14	of	of	ADP
fcis-2052	65	15	accuracy	accuracy	NOUN
fcis-2052	65	16	and	and	CCONJ
fcis-2052	65	17	intelligence	intelligence	NOUN
fcis-2052	65	18	,	,	PUNCT
fcis-2052	65	19	and	and	CCONJ
fcis-2052	65	20	the	the	DET
fcis-2052	65	21	filtering	filter	VERB
fcis-2052	65	22	system	system	NOUN
fcis-2052	65	23	is	be	AUX
fcis-2052	65	24	no	no	DET
fcis-2052	65	25	exception	exception	NOUN
fcis-2052	65	26	.	.	PUNCT
fcis-2052	66	1	the	the	DET
fcis-2052	66	2	34	34	NUM
fcis-2052	66	3	filtering	filter	VERB
fcis-2052	66	4	system	system	NOUN
fcis-2052	66	5	uses	use	VERB
fcis-2052	66	6	the	the	DET
fcis-2052	66	7	evolutionary	evolutionary	ADJ
fcis-2052	66	8	mechanism	mechanism	NOUN
fcis-2052	66	9	of	of	ADP
fcis-2052	66	10	genetic	genetic	ADJ
fcis-2052	66	11	algorithm	algorithm	NOUN
fcis-2052	66	12	to	to	PART
fcis-2052	66	13	track	track	VERB
fcis-2052	66	14	and	and	CCONJ
fcis-2052	66	15	learn	learn	VERB
fcis-2052	66	16	user	user	NOUN
fcis-2052	66	17	interests	interest	NOUN
fcis-2052	66	18	from	from	ADP
fcis-2052	66	19	user	user	NOUN
fcis-2052	66	20	templates	template	NOUN
fcis-2052	66	21	.	.	PUNCT
fcis-2052	67	1	with	with	ADP
fcis-2052	67	2	the	the	DET
fcis-2052	67	3	accuracy	accuracy	NOUN
fcis-2052	67	4	of	of	ADP
fcis-2052	67	5	user	user	NOUN
fcis-2052	67	6	templates	template	NOUN
fcis-2052	67	7	,	,	PUNCT
fcis-2052	67	8	the	the	DET
fcis-2052	67	9	amount	amount	NOUN
fcis-2052	67	10	of	of	ADP
fcis-2052	67	11	user	user	NOUN
fcis-2052	67	12	feedback	feedback	NOUN
fcis-2052	67	13	will	will	AUX
fcis-2052	67	14	continue	continue	VERB
fcis-2052	67	15	to	to	PART
fcis-2052	67	16	decrease	decrease	VERB
fcis-2052	67	17	,	,	PUNCT
fcis-2052	67	18	the	the	DET
fcis-2052	67	19	system	system	NOUN
fcis-2052	67	20	will	will	AUX
fcis-2052	67	21	become	become	VERB
fcis-2052	67	22	more	more	ADV
fcis-2052	67	23	intelligent	intelligent	ADJ
fcis-2052	67	24	,	,	PUNCT
fcis-2052	67	25	and	and	CCONJ
fcis-2052	67	26	the	the	DET
fcis-2052	67	27	adaptive	adaptive	ADJ
fcis-2052	67	28	function	function	NOUN
fcis-2052	67	29	will	will	AUX
fcis-2052	67	30	become	become	VERB
fcis-2052	67	31	stronger	strong	ADJ
fcis-2052	67	32	and	and	CCONJ
fcis-2052	67	33	stronger	strong	ADJ
fcis-2052	67	34	.	.	PUNCT
fcis-2052	68	1	4	4	X
fcis-2052	68	2	.	.	X
fcis-2052	68	3	experimental	experimental	ADJ
fcis-2052	68	4	analysis	analysis	NOUN
fcis-2052	68	5	we	we	PRON
fcis-2052	68	6	selected	select	VERB
fcis-2052	68	7	48	48	NUM
fcis-2052	68	8	web	web	NOUN
fcis-2052	68	9	documents	document	NOUN
fcis-2052	68	10	from	from	ADP
fcis-2052	68	11	the	the	DET
fcis-2052	68	12	documents	document	NOUN
fcis-2052	68	13	downloaded	download	VERB
fcis-2052	68	14	from	from	ADP
fcis-2052	68	15	the	the	DET
fcis-2052	68	16	internet	internet	NOUN
fcis-2052	68	17	for	for	ADP
fcis-2052	68	18	testing	testing	NOUN
fcis-2052	68	19	,	,	PUNCT
fcis-2052	68	20	including	include	VERB
fcis-2052	68	21	24	24	NUM
fcis-2052	68	22	related	relate	VERB
fcis-2052	68	23	documents	document	NOUN
fcis-2052	68	24	,	,	PUNCT
fcis-2052	68	25	4	4	NUM
fcis-2052	68	26	of	of	ADP
fcis-2052	68	27	which	which	PRON
fcis-2052	68	28	are	be	AUX
fcis-2052	68	29	from	from	ADP
fcis-2052	68	30	1	1	NUM
fcis-2052	68	31	kb	kb	PROPN
fcis-2052	68	32	to	to	ADP
fcis-2052	68	33	12	12	NUM
fcis-2052	68	34	kb	kb	NOUN
fcis-2052	68	35	in	in	ADP
fcis-2052	68	36	size	size	NOUN
fcis-2052	68	37	;	;	PUNCT
fcis-2052	68	38	there	there	PRON
fcis-2052	68	39	are	be	VERB
fcis-2052	68	40	24	24	NUM
fcis-2052	68	41	irrelevant	irrelevant	ADJ
fcis-2052	68	42	documents	document	NOUN
fcis-2052	68	43	,	,	PUNCT
fcis-2052	68	44	4	4	NUM
fcis-2052	68	45	of	of	ADP
fcis-2052	68	46	which	which	PRON
fcis-2052	68	47	are	be	AUX
fcis-2052	68	48	from	from	ADP
fcis-2052	68	49	1	1	NUM
fcis-2052	68	50	kb	kb	PROPN
fcis-2052	68	51	to	to	ADP
fcis-2052	68	52	12	12	NUM
fcis-2052	68	53	kb	kb	PROPN
fcis-2052	68	54	in	in	ADP
fcis-2052	68	55	size	size	NOUN
fcis-2052	68	56	.	.	PUNCT
fcis-2052	69	1	according	accord	VERB
fcis-2052	69	2	to	to	ADP
fcis-2052	69	3	the	the	DET
fcis-2052	69	4	traditional	traditional	ADJ
fcis-2052	69	5	method	method	NOUN
fcis-2052	69	6	,	,	PUNCT
fcis-2052	69	7	the	the	DET
fcis-2052	69	8	web	web	NOUN
fcis-2052	69	9	document	document	NOUN
fcis-2052	69	10	is	be	AUX
fcis-2052	69	11	first	first	ADV
fcis-2052	69	12	transformed	transform	VERB
fcis-2052	69	13	into	into	ADP
fcis-2052	69	14	ordinary	ordinary	ADJ
fcis-2052	69	15	text	text	NOUN
fcis-2052	69	16	format	format	NOUN
fcis-2052	69	17	,	,	PUNCT
fcis-2052	69	18	and	and	CCONJ
fcis-2052	69	19	the	the	DET
fcis-2052	69	20	word	word	NOUN
fcis-2052	69	21	segmentation	segmentation	NOUN
fcis-2052	69	22	is	be	AUX
fcis-2052	69	23	carried	carry	VERB
fcis-2052	69	24	out	out	ADP
fcis-2052	69	25	.	.	PUNCT
fcis-2052	70	1	the	the	DET
fcis-2052	70	2	matching	match	VERB
fcis-2052	70	3	feature	feature	NOUN
fcis-2052	70	4	words	word	NOUN
fcis-2052	70	5	are	be	AUX
fcis-2052	70	6	found	find	VERB
fcis-2052	70	7	from	from	ADP
fcis-2052	70	8	the	the	DET
fcis-2052	70	9	word	word	NOUN
fcis-2052	70	10	segmentation	segmentation	NOUN
fcis-2052	70	11	results	result	NOUN
fcis-2052	70	12	,	,	PUNCT
fcis-2052	70	13	and	and	CCONJ
fcis-2052	70	14	then	then	ADV
fcis-2052	70	15	the	the	DET
fcis-2052	70	16	weight	weight	NOUN
fcis-2052	70	17	is	be	AUX
fcis-2052	70	18	calculated	calculate	VERB
fcis-2052	70	19	.	.	PUNCT
fcis-2052	71	1	finally	finally	ADV
fcis-2052	71	2	,	,	PUNCT
fcis-2052	71	3	the	the	DET
fcis-2052	71	4	similarity	similarity	NOUN
fcis-2052	71	5	between	between	ADP
fcis-2052	71	6	the	the	DET
fcis-2052	71	7	web	web	NOUN
fcis-2052	71	8	document	document	NOUN
fcis-2052	71	9	and	and	CCONJ
fcis-2052	71	10	the	the	DET
fcis-2052	71	11	user	user	NOUN
fcis-2052	71	12	template	template	NOUN
fcis-2052	71	13	is	be	AUX
fcis-2052	71	14	calculated	calculate	VERB
fcis-2052	71	15	to	to	PART
fcis-2052	71	16	obtain	obtain	VERB
fcis-2052	71	17	the	the	DET
fcis-2052	71	18	document	document	NOUN
fcis-2052	71	19	category	category	NOUN
fcis-2052	71	20	attribution	attribution	NOUN
fcis-2052	71	21	.	.	PUNCT
fcis-2052	72	1	by	by	ADP
fcis-2052	72	2	identifying	identify	VERB
fcis-2052	72	3	the	the	DET
fcis-2052	72	4	label	label	NOUN
fcis-2052	72	5	meaning	meaning	NOUN
fcis-2052	72	6	of	of	ADP
fcis-2052	72	7	the	the	DET
fcis-2052	72	8	feature	feature	NOUN
fcis-2052	72	9	words	word	NOUN
fcis-2052	72	10	,	,	PUNCT
fcis-2052	72	11	the	the	DET
fcis-2052	72	12	improved	improved	ADJ
fcis-2052	72	13	algorithm	algorithm	NOUN
fcis-2052	72	14	can	can	AUX
fcis-2052	72	15	increase	increase	VERB
fcis-2052	72	16	the	the	DET
fcis-2052	72	17	semantic	semantic	ADJ
fcis-2052	72	18	understanding	understanding	NOUN
fcis-2052	72	19	of	of	ADP
fcis-2052	72	20	the	the	DET
fcis-2052	72	21	document	document	NOUN
fcis-2052	72	22	and	and	CCONJ
fcis-2052	72	23	more	more	ADV
fcis-2052	72	24	accurately	accurately	ADV
fcis-2052	72	25	grasp	grasp	VERB
fcis-2052	72	26	the	the	DET
fcis-2052	72	27	weight	weight	NOUN
fcis-2052	72	28	of	of	ADP
fcis-2052	72	29	the	the	DET
fcis-2052	72	30	feature	feature	NOUN
fcis-2052	72	31	words	word	NOUN
fcis-2052	72	32	in	in	ADP
fcis-2052	72	33	the	the	DET
fcis-2052	72	34	document	document	NOUN
fcis-2052	72	35	.	.	PUNCT
fcis-2052	73	1	according	accord	VERB
fcis-2052	73	2	to	to	ADP
fcis-2052	73	3	the	the	DET
fcis-2052	73	4	improved	improved	ADJ
fcis-2052	73	5	method	method	NOUN
fcis-2052	73	6	,	,	PUNCT
fcis-2052	73	7	the	the	DET
fcis-2052	73	8	feature	feature	NOUN
fcis-2052	73	9	word	word	NOUN
fcis-2052	73	10	is	be	AUX
fcis-2052	73	11	directly	directly	ADV
fcis-2052	73	12	taken	take	VERB
fcis-2052	73	13	from	from	ADP
fcis-2052	73	14	the	the	DET
fcis-2052	73	15	user	user	NOUN
fcis-2052	73	16	template	template	NOUN
fcis-2052	73	17	,	,	PUNCT
fcis-2052	73	18	its	its	PRON
fcis-2052	73	19	position	position	NOUN
fcis-2052	73	20	and	and	CCONJ
fcis-2052	73	21	occurrence	occurrence	NOUN
fcis-2052	73	22	times	time	NOUN
fcis-2052	73	23	in	in	ADP
fcis-2052	73	24	the	the	DET
fcis-2052	73	25	document	document	NOUN
fcis-2052	73	26	are	be	AUX
fcis-2052	73	27	found	find	VERB
fcis-2052	73	28	,	,	PUNCT
fcis-2052	73	29	the	the	DET
fcis-2052	73	30	weight	weight	NOUN
fcis-2052	73	31	calculation	calculation	NOUN
fcis-2052	73	32	formula	formula	NOUN
fcis-2052	73	33	is	be	AUX
fcis-2052	73	34	brought	bring	VERB
fcis-2052	73	35	in	in	ADP
fcis-2052	73	36	,	,	PUNCT
fcis-2052	73	37	and	and	CCONJ
fcis-2052	73	38	then	then	ADV
fcis-2052	73	39	the	the	DET
fcis-2052	73	40	similarity	similarity	NOUN
fcis-2052	73	41	between	between	ADP
fcis-2052	73	42	the	the	DET
fcis-2052	73	43	user	user	NOUN
fcis-2052	73	44	template	template	NOUN
fcis-2052	73	45	and	and	CCONJ
fcis-2052	73	46	the	the	DET
fcis-2052	73	47	feature	feature	NOUN
fcis-2052	73	48	word	word	NOUN
fcis-2052	73	49	is	be	AUX
fcis-2052	73	50	calculated	calculate	VERB
fcis-2052	73	51	to	to	PART
fcis-2052	73	52	determine	determine	VERB
fcis-2052	73	53	its	its	PRON
fcis-2052	73	54	category	category	NOUN
fcis-2052	73	55	.	.	PUNCT
fcis-2052	74	1	the	the	DET
fcis-2052	74	2	precision	precision	NOUN
fcis-2052	74	3	is	be	AUX
fcis-2052	74	4	improved	improve	VERB
fcis-2052	74	5	.	.	PUNCT
fcis-2052	75	1	in	in	ADP
fcis-2052	75	2	this	this	DET
fcis-2052	75	3	experiment	experiment	NOUN
fcis-2052	75	4	,	,	PUNCT
fcis-2052	75	5	the	the	DET
fcis-2052	75	6	number	number	NOUN
fcis-2052	75	7	of	of	ADP
fcis-2052	75	8	relevant	relevant	ADJ
fcis-2052	75	9	documents	document	NOUN
fcis-2052	75	10	returned	return	VERB
fcis-2052	75	11	by	by	ADP
fcis-2052	75	12	the	the	DET
fcis-2052	75	13	traditional	traditional	ADJ
fcis-2052	75	14	algorithm	algorithm	NOUN
fcis-2052	75	15	is	be	AUX
fcis-2052	75	16	16	16	NUM
fcis-2052	75	17	,	,	PUNCT
fcis-2052	75	18	and	and	CCONJ
fcis-2052	75	19	the	the	DET
fcis-2052	75	20	precision	precision	NOUN
fcis-2052	75	21	ratio	ratio	NOUN
fcis-2052	75	22	is	be	AUX
fcis-2052	75	23	0.333	0.333	NUM
fcis-2052	75	24	;	;	PUNCT
fcis-2052	75	25	the	the	DET
fcis-2052	75	26	number	number	NOUN
fcis-2052	75	27	of	of	ADP
fcis-2052	75	28	related	related	ADJ
fcis-2052	75	29	documents	document	NOUN
fcis-2052	75	30	returned	return	VERB
fcis-2052	75	31	by	by	ADP
fcis-2052	75	32	the	the	DET
fcis-2052	75	33	improved	improved	ADJ
fcis-2052	75	34	algorithm	algorithm	NOUN
fcis-2052	75	35	is	be	AUX
fcis-2052	75	36	20	20	NUM
fcis-2052	75	37	,	,	PUNCT
fcis-2052	75	38	and	and	CCONJ
fcis-2052	75	39	the	the	DET
fcis-2052	75	40	precision	precision	NOUN
fcis-2052	75	41	ratio	ratio	NOUN
fcis-2052	75	42	is	be	AUX
fcis-2052	75	43	0.417	0.417	NUM
fcis-2052	75	44	.	.	PUNCT
fcis-2052	76	1	acknowledgments	acknowledgment	NOUN
fcis-2052	76	2	this	this	DET
fcis-2052	76	3	work	work	NOUN
fcis-2052	76	4	was	be	AUX
fcis-2052	76	5	supported	support	VERB
fcis-2052	76	6	by	by	ADP
fcis-2052	76	7	the	the	DET
fcis-2052	76	8	science	science	NOUN
fcis-2052	76	9	and	and	CCONJ
fcis-2052	76	10	technology	technology	NOUN
fcis-2052	76	11	project	project	NOUN
fcis-2052	76	12	of	of	ADP
fcis-2052	76	13	jiangxi	jiangxi	PROPN
fcis-2052	76	14	provincial	provincial	PROPN
fcis-2052	76	15	department	department	PROPN
fcis-2052	76	16	of	of	ADP
fcis-2052	76	17	education	education	NOUN
fcis-2052	76	18	,	,	PUNCT
fcis-2052	76	19	and	and	CCONJ
fcis-2052	76	20	the	the	DET
fcis-2052	76	21	project	project	NOUN
fcis-2052	76	22	number	number	NOUN
fcis-2052	76	23	is	be	AUX
fcis-2052	76	24	gjj170797	gjj170797	NOUN
fcis-2052	76	25	.	.	PUNCT
fcis-2052	77	1	references	reference	NOUN
fcis-2052	77	2	[	[	X
fcis-2052	77	3	1	1	NUM
fcis-2052	77	4	]	]	X
fcis-2052	77	5	liu	liu	PROPN
fcis-2052	77	6	wei	wei	PROPN
fcis-2052	77	7	.	.	PUNCT
fcis-2052	78	1	research	research	NOUN
fcis-2052	78	2	on	on	ADP
fcis-2052	78	3	content	content	NOUN
fcis-2052	78	4	based	base	VERB
fcis-2052	78	5	bad	bad	ADJ
fcis-2052	78	6	web	web	NOUN
fcis-2052	78	7	page	page	NOUN
fcis-2052	78	8	information	information	NOUN
fcis-2052	78	9	filtering	filtering	NOUN
fcis-2052	78	10	method	method	NOUN
fcis-2052	79	1	[	[	X
fcis-2052	79	2	d	d	X
fcis-2052	79	3	]	]	X
fcis-2052	79	4	.	.	PUNCT
fcis-2052	80	1	jilin	jilin	PROPN
fcis-2052	80	2	university	university	PROPN
fcis-2052	80	3	.	.	PUNCT
fcis-2052	81	1	2013	2013	NUM
fcis-2052	81	2	.	.	PUNCT
fcis-2052	82	1	[	[	X
fcis-2052	82	2	2	2	X
fcis-2052	82	3	]	]	X
fcis-2052	82	4	sun	sun	PROPN
fcis-2052	82	5	kai	kai	PROPN
fcis-2052	82	6	.	.	PUNCT
fcis-2052	82	7	research	research	NOUN
fcis-2052	82	8	on	on	ADP
fcis-2052	82	9	bad	bad	ADJ
fcis-2052	82	10	content	content	NOUN
fcis-2052	82	11	web	web	NOUN
fcis-2052	82	12	page	page	NOUN
fcis-2052	82	13	filtering	filtering	NOUN
fcis-2052	82	14	technology	technology	NOUN
fcis-2052	83	1	[	[	X
fcis-2052	83	2	d	d	X
fcis-2052	83	3	]	]	X
fcis-2052	83	4	.	.	PUNCT
fcis-2052	84	1	liaoning	liaoning	PROPN
fcis-2052	84	2	university	university	PROPN
fcis-2052	84	3	of	of	ADP
fcis-2052	84	4	petrochemical	petrochemical	NOUN
fcis-2052	84	5	technology	technology	NOUN
fcis-2052	84	6	.	.	PUNCT
fcis-2052	85	1	2012	2012	NUM
fcis-2052	85	2	.	.	PUNCT
fcis-2052	86	1	[	[	X
fcis-2052	86	2	3	3	X
fcis-2052	86	3	]	]	X
fcis-2052	86	4	qiu	qiu	PROPN
fcis-2052	86	5	siheng	siheng	PROPN
fcis-2052	86	6	.	.	PUNCT
fcis-2052	87	1	research	research	NOUN
fcis-2052	87	2	and	and	CCONJ
fcis-2052	87	3	design	design	NOUN
fcis-2052	87	4	of	of	ADP
fcis-2052	87	5	wireless	wireless	ADJ
fcis-2052	87	6	internet	internet	NOUN
fcis-2052	87	7	bad	bad	ADJ
fcis-2052	87	8	information	information	NOUN
fcis-2052	87	9	filtering	filter	VERB
fcis-2052	87	10	system	system	NOUN
fcis-2052	88	1	[	[	X
fcis-2052	88	2	d	d	X
fcis-2052	88	3	]	]	X
fcis-2052	88	4	.	.	PUNCT
fcis-2052	89	1	beijing	beijing	PROPN
fcis-2052	89	2	university	university	PROPN
fcis-2052	89	3	of	of	ADP
fcis-2052	89	4	posts	post	NOUN
fcis-2052	89	5	and	and	CCONJ
fcis-2052	89	6	telecommunications	telecommunication	NOUN
fcis-2052	89	7	.	.	PUNCT
fcis-2052	90	1	2009	2009	NUM
fcis-2052	90	2	.	.	PUNCT
fcis-2052	91	1	[	[	X
fcis-2052	91	2	4	4	X
fcis-2052	91	3	]	]	X
fcis-2052	91	4	zeng	zeng	PROPN
fcis-2052	91	5	zhiyuan	zhiyuan	PROPN
fcis-2052	91	6	,	,	PUNCT
fcis-2052	91	7	zhang	zhang	PROPN
fcis-2052	91	8	li	li	PROPN
fcis-2052	91	9	.	.	PUNCT
fcis-2052	92	1	an	an	DET
fcis-2052	92	2	improved	improved	ADJ
fcis-2052	92	3	algorithm	algorithm	NOUN
fcis-2052	92	4	for	for	ADP
fcis-2052	92	5	web	web	NOUN
fcis-2052	92	6	page	page	NOUN
fcis-2052	92	7	text	text	NOUN
fcis-2052	92	8	representation	representation	NOUN
fcis-2052	92	9	based	base	VERB
fcis-2052	92	10	on	on	ADP
fcis-2052	92	11	vector	vector	NOUN
fcis-2052	92	12	space	space	NOUN
fcis-2052	92	13	model	model	NOUN
fcis-2052	93	1	[	[	X
fcis-2052	93	2	j	j	X
fcis-2052	93	3	]	]	X
fcis-2052	93	4	.	.	PUNCT
fcis-2052	94	1	computer	computer	NOUN
fcis-2052	94	2	engineering	engineering	NOUN
fcis-2052	94	3	.	.	PUNCT
fcis-2052	95	1	2006	2006	NUM
fcis-2052	95	2	(	(	PUNCT
fcis-2052	95	3	03	03	NUM
fcis-2052	95	4	)	)	PUNCT
fcis-2052	95	5	.	.	PUNCT
fcis-2052	96	1	[	[	X
fcis-2052	96	2	5	5	NUM
fcis-2052	96	3	]	]	X
fcis-2052	96	4	tang	tang	PROPN
fcis-2052	96	5	jiangang	jiangang	PROPN
fcis-2052	96	6	,	,	PUNCT
fcis-2052	96	7	xiong	xiong	PROPN
fcis-2052	96	8	guoping	guoping	PROPN
fcis-2052	96	9	.	.	PUNCT
fcis-2052	97	1	research	research	NOUN
fcis-2052	97	2	and	and	CCONJ
fcis-2052	97	3	practice	practice	NOUN
fcis-2052	97	4	of	of	ADP
fcis-2052	97	5	adaptive	adaptive	ADJ
fcis-2052	97	6	bad	bad	ADJ
fcis-2052	97	7	web	web	NOUN
fcis-2052	97	8	page	page	NOUN
fcis-2052	97	9	filtering	filter	VERB
fcis-2052	97	10	mode	mode	NOUN
fcis-2052	98	1	[	[	X
fcis-2052	98	2	j	j	X
fcis-2052	98	3	]	]	X
fcis-2052	98	4	.	.	PUNCT
fcis-2052	99	1	computer	computer	NOUN
fcis-2052	99	2	engineering	engineering	NOUN
fcis-2052	99	3	and	and	CCONJ
fcis-2052	99	4	design	design	NOUN
fcis-2052	99	5	.	.	PUNCT
fcis-2052	100	1	2008	2008	NUM
fcis-2052	100	2	(	(	PUNCT
fcis-2052	100	3	20	20	NUM
fcis-2052	100	4	)	)	PUNCT
fcis-2052	100	5	.	.	PUNCT