Finding More Bilingual Webpages with High Credibility via Link Analysis

Chengzhi Zhang; Xuchen Yao; Chunyu Kit

Finding More Bilingual Webpages with High Credibility via Link Analysis

Chengzhi Zhang
, Xuchen Yao
, Chunyu Kit

Department of Linguistics and Translation

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

4 Citations (Scopus)

30 Downloads (CityUHK Scholars)

Abstract

This paper presents an efficient approach to finding more bilingual webpage pairs with high credibility via link analysis, using little prior knowledge or heuristics. It extends from a previous algorithm that takes the number of bilingual URL pairs that a key (i.e., a URL pairing pattern) can match as the objective function to search for the best set of keys yielding the greatest number of webpage pairs within targeted bilingual websites. Enhanced algorithms are proposed to match more bilingual webpages following the credibility based on statistical analysis of the link relationship of the seed websites available. With about 12,800 seed websites as test set, the enhanced algorithms improve precision over baseline by more than 5%, from 94.06% to 99.40%, and hence find above 20% more true bilingual URL pairs, illustrating that significantly more bilingual webpages with high credibility can be mined with the help of the link analysis. © 2013 Computational Linguistics. All rights reserved.

Original language	English
Title of host publication	ACL 2013 - Sixth Workshop on Building and Using Comparable Corpora
Subtitle of host publication	Proceedings of the Workshop
Publisher	Association for Computational Linguistics
Pages	138-143
ISBN (Print)	9781937284602
Publication status	Published - Aug 2013
Event	6th Workshop on Building and Using Comparable Corpora (BUCC 2013) Co-located with 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013) - Sofia, Bulgaria Duration: 8 Aug 2013 → 8 Aug 2013 https://aclanthology.org/W13-25 https://comparable.limsi.fr/bucc2013/

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)	0736-587X

Conference

Conference	6th Workshop on Building and Using Comparable Corpora (BUCC 2013) Co-located with 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013)
Place	Bulgaria
City	Sofia
Period	8/08/13 → 8/08/13
Internet address	https://aclanthology.org/W13-25 https://comparable.limsi.fr/bucc2013/

Publisher's Copyright Statement

This full text is made available under CC-BY-NC-SA 3.0. https://creativecommons.org/licenses/by-nc-sa/3.0/

Access Output

276651498.pdfFinal Published version, 502 KBLicence: CC BY-NC-SA

https://aclanthology.org/W13-2517/

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Zhang, C., Yao, X., & Kit, C. (2013). Finding More Bilingual Webpages with High Credibility via Link Analysis. In ACL 2013 - Sixth Workshop on Building and Using Comparable Corpora: Proceedings of the Workshop (pp. 138-143). (Proceedings of the Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics. https://aclanthology.org/W13-2517/

@inproceedings{f4d20add5ff74ab38ae60bc8282fdf85,

title = "Finding More Bilingual Webpages with High Credibility via Link Analysis",

abstract = "This paper presents an efficient approach to finding more bilingual webpage pairs with high credibility via link analysis, using little prior knowledge or heuristics. It extends from a previous algorithm that takes the number of bilingual URL pairs that a key (i.e., a URL pairing pattern) can match as the objective function to search for the best set of keys yielding the greatest number of webpage pairs within targeted bilingual websites. Enhanced algorithms are proposed to match more bilingual webpages following the credibility based on statistical analysis of the link relationship of the seed websites available. With about 12,800 seed websites as test set, the enhanced algorithms improve precision over baseline by more than 5\%, from 94.06\% to 99.40\%, and hence find above 20\% more true bilingual URL pairs, illustrating that significantly more bilingual webpages with high credibility can be mined with the help of the link analysis. {\textcopyright} 2013 Computational Linguistics. All rights reserved.",

author = "Chengzhi Zhang and Xuchen Yao and Chunyu Kit",

year = "2013",

month = aug,

language = "English",

isbn = "9781937284602",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

pages = "138--143",

booktitle = "ACL 2013 - Sixth Workshop on Building and Using Comparable Corpora",

address = "United States",

note = "6th Workshop on Building and Using Comparable Corpora (BUCC 2013) Co-located with 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013) ; Conference date: 08-08-2013 Through 08-08-2013",

url = "https://aclanthology.org/W13-25, https://comparable.limsi.fr/bucc2013/",

}

Zhang, C, Yao, X & Kit, C 2013, Finding More Bilingual Webpages with High Credibility via Link Analysis. in ACL 2013 - Sixth Workshop on Building and Using Comparable Corpora: Proceedings of the Workshop. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, pp. 138-143, 6th Workshop on Building and Using Comparable Corpora (BUCC 2013) Co-located with 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013), Sofia, Bulgaria, 8/08/13. <https://aclanthology.org/W13-2517/>

Finding More Bilingual Webpages with High Credibility via Link Analysis. / Zhang, Chengzhi; Yao, Xuchen; Kit, Chunyu.
ACL 2013 - Sixth Workshop on Building and Using Comparable Corpora: Proceedings of the Workshop. Association for Computational Linguistics, 2013. p. 138-143 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Finding More Bilingual Webpages with High Credibility via Link Analysis

AU - Zhang, Chengzhi

AU - Yao, Xuchen

AU - Kit, Chunyu

PY - 2013/8

Y1 - 2013/8

N2 - This paper presents an efficient approach to finding more bilingual webpage pairs with high credibility via link analysis, using little prior knowledge or heuristics. It extends from a previous algorithm that takes the number of bilingual URL pairs that a key (i.e., a URL pairing pattern) can match as the objective function to search for the best set of keys yielding the greatest number of webpage pairs within targeted bilingual websites. Enhanced algorithms are proposed to match more bilingual webpages following the credibility based on statistical analysis of the link relationship of the seed websites available. With about 12,800 seed websites as test set, the enhanced algorithms improve precision over baseline by more than 5%, from 94.06% to 99.40%, and hence find above 20% more true bilingual URL pairs, illustrating that significantly more bilingual webpages with high credibility can be mined with the help of the link analysis. © 2013 Computational Linguistics. All rights reserved.

AB - This paper presents an efficient approach to finding more bilingual webpage pairs with high credibility via link analysis, using little prior knowledge or heuristics. It extends from a previous algorithm that takes the number of bilingual URL pairs that a key (i.e., a URL pairing pattern) can match as the objective function to search for the best set of keys yielding the greatest number of webpage pairs within targeted bilingual websites. Enhanced algorithms are proposed to match more bilingual webpages following the credibility based on statistical analysis of the link relationship of the seed websites available. With about 12,800 seed websites as test set, the enhanced algorithms improve precision over baseline by more than 5%, from 94.06% to 99.40%, and hence find above 20% more true bilingual URL pairs, illustrating that significantly more bilingual webpages with high credibility can be mined with the help of the link analysis. © 2013 Computational Linguistics. All rights reserved.

UR - https://www.scopus.com/pages/publications/84921381997

UR - https://www.scopus.com/pages/publications/84921381997#tab=impact

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781937284602

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 138

EP - 143

BT - ACL 2013 - Sixth Workshop on Building and Using Comparable Corpora

PB - Association for Computational Linguistics

T2 - 6th Workshop on Building and Using Comparable Corpora (BUCC 2013) Co-located with 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013)

Y2 - 8 August 2013 through 8 August 2013

ER -

Finding More Bilingual Webpages with High Credibility via Link Analysis

Abstract

Publication series

Conference

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this