Cross-lingual opinion analysis via negative transfer detection

Lin Gui; Ruifeng Xu; Qin Lu; Jun Xu; Jian Xu; Bin Liu; Xiaolong Wang

Cross-lingual opinion analysis via negative transfer detection

Lin Gui, Ruifeng Xu, Qin Lu, Jun Xu, Jian Xu, Bin Liu, Xiaolong Wang

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

29 Citations (Scopus)

Abstract

Transfer learning has been used in opinion analysis to make use of available language resources for other resource scarce languages. However, the cumulative class noise in transfer learning adversely affects performance when more training data is used. In this paper, we propose a novel method in transductive transfer learning to identify noises through the detection of negative transfers. Evaluation on NLP&CC 2013 cross-lingual opinion analysis dataset shows that our approach outperforms the state-of-the-art systems. More significantly, our system shows a monotonic increase trend in performance improvement when more training data are used.

Original language	English
Title of host publication	Long Papers
Publisher	Association for Computational Linguistics (ACL)
Pages	860-865
Number of pages	6
Volume	2
ISBN (Print)	9781937284732
Publication status	Published - 1 Jan 2014
Event	52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Baltimore, MD, United States Duration: 22 Jun 2014 → 27 Jun 2014

Conference

Conference	52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014
Country/Territory	United States
City	Baltimore, MD
Period	22/06/14 → 27/06/14

ASJC Scopus subject areas

Language and Linguistics
Linguistics and Language

Cite this

@inproceedings{0e0df901233c4279a7322bb92dfe527d,

title = "Cross-lingual opinion analysis via negative transfer detection",

abstract = "Transfer learning has been used in opinion analysis to make use of available language resources for other resource scarce languages. However, the cumulative class noise in transfer learning adversely affects performance when more training data is used. In this paper, we propose a novel method in transductive transfer learning to identify noises through the detection of negative transfers. Evaluation on NLP&CC 2013 cross-lingual opinion analysis dataset shows that our approach outperforms the state-of-the-art systems. More significantly, our system shows a monotonic increase trend in performance improvement when more training data are used.",

author = "Lin Gui and Ruifeng Xu and Qin Lu and Jun Xu and Jian Xu and Bin Liu and Xiaolong Wang",

year = "2014",

month = jan,

day = "1",

language = "English",

isbn = "9781937284732",

volume = "2",

pages = "860--865",

booktitle = "Long Papers",

publisher = "Association for Computational Linguistics (ACL)",

note = "52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 ; Conference date: 22-06-2014 Through 27-06-2014",

}

TY - GEN

T1 - Cross-lingual opinion analysis via negative transfer detection

AU - Gui, Lin

AU - Xu, Ruifeng

AU - Lu, Qin

AU - Xu, Jun

AU - Xu, Jian

AU - Liu, Bin

AU - Wang, Xiaolong

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Transfer learning has been used in opinion analysis to make use of available language resources for other resource scarce languages. However, the cumulative class noise in transfer learning adversely affects performance when more training data is used. In this paper, we propose a novel method in transductive transfer learning to identify noises through the detection of negative transfers. Evaluation on NLP&CC 2013 cross-lingual opinion analysis dataset shows that our approach outperforms the state-of-the-art systems. More significantly, our system shows a monotonic increase trend in performance improvement when more training data are used.

AB - Transfer learning has been used in opinion analysis to make use of available language resources for other resource scarce languages. However, the cumulative class noise in transfer learning adversely affects performance when more training data is used. In this paper, we propose a novel method in transductive transfer learning to identify noises through the detection of negative transfers. Evaluation on NLP&CC 2013 cross-lingual opinion analysis dataset shows that our approach outperforms the state-of-the-art systems. More significantly, our system shows a monotonic increase trend in performance improvement when more training data are used.

UR - http://www.scopus.com/inward/record.url?scp=84906925062&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SN - 9781937284732

VL - 2

SP - 860

EP - 865

BT - Long Papers

PB - Association for Computational Linguistics (ACL)

T2 - 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014

Y2 - 22 June 2014 through 27 June 2014

ER -

Cross-lingual opinion analysis via negative transfer detection

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this