Cross-lingual implicit discourse relation recognition with co-training

Yao-jie LU; Mu XU; Chang-xing WU; De-yi XIONG; Hong-ji WANG; Jin-song SU

doi:10.1631/FITEE.1601865

Your Location：

Home >

Browse articles >

Cross-lingual implicit discourse relation recognition with co-training

Regular Papers | Updated：2022-05-19

- Cross-lingual implicit discourse relation recognition with co-training
- 基于协同学习的跨语言隐式篇章关系识别
- Frontiers of Information Technology & Electronic Engineering Vol. 19, Issue 5, Pages: 651-661(2018)
- Affiliations：
  
  School of Software, Xiamen University, Xiamen 361005, China
  State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China
  Institute of Software, Chinese Academy of Sciences, Beijing 100190, China
  Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Suzhou 215006, China
- Author bio：
  
  Jin-song SU, E-mail: jssu@xmu.edu.cn
- Funds：
- DOI：10.1631/FITEE.1601865
  CLC： TP391.1
- Received：24 December 2016，
  
  Revised：2018-;5-;8，
  
  Published：2018-05
- Accepted：
Scan QR Code
Yao-jie LU, Mu XU, Chang-xing WU, et al. Cross-lingual implicit discourse relation recognition with co-training[J]. Frontiers of Information Technology & Electronic Engineering, 2018, 19(5): 651-661.
DOI：

Yao-jie LU, Mu XU, Chang-xing WU, et al. Cross-lingual implicit discourse relation recognition with co-training[J]. Frontiers of Information Technology & Electronic Engineering, 2018, 19(5): 651-661. DOI： 10.1631/FITEE.1601865.

摘要

标注语料库的缺乏阻碍了中文隐式篇章关系识别研究的进展，而在其他语言（如英语）中存在一些可用的篇章关系语料库。提出一个跨语言的隐式篇章关系识别框架，该框架可利用英语语料库完成中文隐式篇章关系识别任务。使用机器翻译从带标签的英语篇章关系语料库生成中文实例。基于该方法，每个实例都有两个独立视角：中文和英文。然后，利用联合训练方式，分别基于中文和英文视角学习两个分类器，同时利用无标签中文数据帮助完成中文隐式篇章关系识别。实验结果证明该方法有效。

Abstract

A lack of labeled corpora obstructs the research progress on implicit discourse relation recognition (DRR) for Chinese

while there are some available discourse corpora in other languages

such as English. In this paper

we propose a cross-lingual implicit DRR framework that exploits an available English corpus for the Chinese DRR task. We use machine translation to generate Chinese instances from a labeled English discourse corpus. In this way

each instance has two independent views: Chinese and English views. Then we train two classifiers in Chinese and English in a co-training way

which exploits unlabeled Chinese data to implement better implicit DRR for Chinese. Experimental results demonstrate the effectiveness of our method.

关键词

Keywords

references

O Biran , , , K McKeown . . Aggregated word pair features for implicit discourse relation disambiguation . . Proc 51 st Annual Meeting of the Association for Computational Linguistics , , 2013 . . p.69 - - 73 . . DOI: 10.7916/D8PN9FZ4 http://doi.org/10.7916/D8PN9FZ4 . .

A Blum , , , T Mitchell . . Combining labeled and unlabeled data with cotraining . . Proc 11 th Annual Conf on Computational Learning Theory , , 1998 . . p.92 - - 100 . . DOI: 10.1145/279943.279962 http://doi.org/10.1145/279943.279962 . .

C Braud , , , P Denis . . Comparing word representations for implicit discourse relation classification . . Proc Conf on Empirical Methods in Natural Language Processing , , 2015 . . p.2201 - - 2211 . . DOI: 10.18653/v1/d15-1262 http://doi.org/10.18653/v1/d15-1262 . .

L Carlson , , , D Marcu , , , M Okurowski . . Building a discourse-tagged corpus in the framework of rhetorical structure theory . . Proc 2 nd SIGDIAL Workshop on Discourse and Dialogue , , 2001 . . p.1 - - 10 . . DOI: 10.3115/1118078.1118083 http://doi.org/10.3115/1118078.1118083 . .

J Chen , , , Q Zhang , , , P Liu , , , 等 . . Implicit discourse relation detection via a deep architecture with gated relevance network . . Proc 54 th Annual Meeting of the Association for Computational Linguistics , , 2016 . . p.1726 - - 1735 . . DOI: 10.18653/v1/p16-1163 http://doi.org/10.18653/v1/p16-1163 . .

L Chen . . English and Chinese Discourse Structure Dimension Theory and Practice . . PhD Thesis, Shanghai International Studies University, China , , 2006 . . .

C Chiarcos . . Towards the unsupervised acquisition of discourse relations . . Proc 50 th Annual Meeting of the Association for Computational Linguistics , , 2012 . . p.213 - - 217 . . . .

P Cimiano , , , U Reyle , , , J Šarić . . Ontology-driven discourse analysis for information extraction . . Data Knowl Eng , , 2005 . . 55 ( ( 1 ): ): 59 - - 83 . . DOI: 10.1016/j.datak.2004.11.009 http://doi.org/10.1016/j.datak.2004.11.009 . .

S Clark , , , J Curran , , , M Osborne . . Bootstrapping POStaggers using unlabelled data . . Proc 7 th Conf on Natural Language Learning , , 2003 . . p.49 - - 55 . . DOI: 10.3115/1119176.1119183 http://doi.org/10.3115/1119176.1119183 . .

F Guzmán , , , S Joty , , , L Màrquez , , , 等 . . Using discourse structure improves machine translation evaluation . . Proc 52 nd Annual Meeting of the Association for Computational Linguistics , , 2014 . . p.687 - - 698 . . DOI: 10.3115/v1/p14-1065 http://doi.org/10.3115/v1/p14-1065 . .

H Hernault , , , D Bollegala , , , M Ishizuka . . Towards semisupervised classification of discourse relations using feature correlations . . Proc SIGDIAL Conf and the 11 th Annual Meeting of the Special Interest Group on Discourse and Dialogue , , 2010 . . p.55 - - 58 . . . .

H Huang , , , H Chen . . Chinese discourse relation recognition . . Proc 5 th Int Joint Conf on Natural Language Processing , , 2011 . . p.1442 - - 1446 . . . .

S Jain , , , S Batra . . Cross lingual sentiment analysis using modified BRAE . . Proc Conf on Empirical Methods in Natural Language Processing , , 2015 . . p.159 - - 168 . . DOI: 10.18653/v1/d15-1016 http://doi.org/10.18653/v1/d15-1016 . .

Y Ji , , , J Eisenstein . . One vector is not enough: entityaugmented distributed semantics for discourse relations . . Trans Assoc Comput Ling , , 2015 . . 3 329 - - 344 . . . .

Y Ji , , , G Haffari , , , J Eisenstein . . A latent variable recurrent neural network for discourse relation language models . . Proc Conf North American Chapter of the Association for Computational Linguistics on Human Language Technologies , , 2016 . . p.332 - - 342 . . DOI: 10.18653/v1/n16-1037 http://doi.org/10.18653/v1/n16-1037 . .

M Laali , , , L Kosseim . . Inducing discourse connectives from parallel texts . . Proc 25 th Int Conf on Computational Linguistics , , 2014 . . p.610 - - 619 . . . .

M Lan , , , Y Xu , , , Z Niu . . Leveraging synthetic discourse data via multi-task learning for implicit discourse relation recognition . . Proc 51 st Annual Meeting of the Association for Computational Linguistics , , 2013 . . p.476 - - 485 . . . .

J Li , , , M Carpuat , , , A Nenkova . . Cross-lingual discourse relation analysis: a corpus study and a semi-supervised classification system . . Proc 25 th Int Conf on Computational Linguistics , , 2014 . . p.577 - - 587 . . . .

Y Li , , , W Feng , , , J Sun , , , 等 . . Building Chinese discourse corpus with connective-driven dependency tree structure . . Proc Conf on Empirical Methods in Natural Language Processing , , 2014 . . p.2105 - - 2114 . . DOI: 10.3115/v1/d14-1224 http://doi.org/10.3115/v1/d14-1224 . .

Z Lin , , , M Kan , , , H Ng . . Recognizing implicit discourse relations in the Penn discourse treebank . . Proc Conf on Empirical Methods in Natural Language Processing , , 2009 . . p.343 - - 351 . . DOI: 10.3115/1699510.1699555 http://doi.org/10.3115/1699510.1699555 . .

Y Liu , , , S Li , , , X Zhang , , , 等 . . Implicit discourse relation classification via multi-task neural networks . . Proc 30 th Conf on Artificial Intelligence , , 2016 . . p.2750 - - 2756 . . . .

A Louis , , , A Joshi , , , R Prasad , , , 等 . . Using entity features to classify implicit discourse relations . . Proc 11 th Annual Meeting of the Special Interest Group on Discourse and Dialogue , , 2010 . . p.59 - - 62 . . . .

D Marcu , , , A Echihabi . . An unsupervised approach to recognizing discourse relations . . Proc 40 th Annual Meeting of the Association for Computational Linguistics , , 2002 . . p.368 - - 375 . . DOI: 10.3115/1073083.1073145 http://doi.org/10.3115/1073083.1073145 . .

E Miltsakaki , , , N Dinesh , , , R Prasad , , , 等 . . Experiments on sense annotations and sense disambiguation of discourse connectives . . Proc 4 th Workshop on Treebanks and Linguistic Theories , , 2005 . . p.1 - - 13 . . . .

Y Ming . . Rhetorical structure annotation of Chinese news commentaries . . J Chin Inform Proc , , 2008 . . 22 ( ( 4 ): ): 19 - - 23 . . . .

V Ng , , , C Cardie . . Weakly supervised natural language learning without redundant views . . Proc Conf North American Chapter of the Association for Computational Linguistics on Human Language Technology , , 2003 . . p.94 - - 101 . . DOI: 10.3115/1073445.1073468 http://doi.org/10.3115/1073445.1073468 . .

J Park , , , C Cardie . . Improving implicit discourse relation recognition through feature set optimization . . Proc 13 th Annual Meeting of the Special Interest Group on Discourse and Dialogue , , 2012 . . p.108 - - 112 . . . .

E Pitler , , , A Nenkova . . Using syntax to disambiguate explicit discourse connectives in text . . Proc ACL-IJCNLP Conf , , 2009 . . p.13 - - 16 . . DOI: 10.3115/1667583.1667589 http://doi.org/10.3115/1667583.1667589 . .

E Pitler , , , A Louis , , , A Nenkova . . Automatic sense prediction for implicit discourse relations in text . . Proc of the Joint Conf 47 th Annual Meeting of the ACL and the 4 th Int Joint Conf on Natural Language Processing of the AFNLP , , 2009 . . p.683 - - 691 . . DOI: 10.3115/1690219.1690241 http://doi.org/10.3115/1690219.1690241 . .

R Prasad , , , N Dinesh , , , A Lee , , , 等 . . The Penn discourse treebank 2.0 . . Proc Int Conf on Language Resources and Evaluation , , 2008 . . p.2961 - - 2968 . . . .

L Qian , , , H Hui , , , Y Hu , , , 等 . . Bilingual active learning for relation classification via pseudo parallel corpora . . Proc 52 nd Annual Meeting of the Association for Computational Linguistics , , 2014 . . p.582 - - 592 . . DOI: 10.3115/v1/p14-1055 http://doi.org/10.3115/v1/p14-1055 . .

L Qin , , , Z Zhang , , , H Zhao . . A stacking gated neural architecture for implicit discourse relation classification . . Proc Conf on Empirical Methods in Natural Language Processing , , 2016 . . p.2263 - - 2270 . . DOI: 10.18653/v1/d16-1246 http://doi.org/10.18653/v1/d16-1246 . .

A Rutherford , , , N Xue . . Discovering implicit discourse relations through brown cluster pair representation and coreference patterns . . Proc 14 th Conf European Chapter of the Association for Computational Linguistics , , 2014 . . p.645 - - 654 . . DOI: 10.3115/v1/e14-1068 http://doi.org/10.3115/v1/e14-1068 . .

A Rutherford , , , N Xue . . Improving the inference of implicit discourse relations via classifying explicit discourse connectives . . Proc Conf of the North American Chapter of the Association for Computational Linguistics on Human Language Technologies , , 2015 . . p.799 - - 808 . . DOI: 10.3115/v1/n15-1081 http://doi.org/10.3115/v1/n15-1081 . .

A Rutherford , , , V Demberg , , , N Xue . . Neural network models for implicit discourse relation classification in English and Chinese without surface features . . http://arxiv.org/abs/1606.01990 , , 2016 . . .

A Sarkar . . Applying co-training methods to statistical parsing . . Proc 2 nd Meeting of the North American Chapter of the Association for Computational Linguistics on Language Technologies , , 2001 . . p.1 - - 8 . . DOI: 10.3115/1073336.1073359 http://doi.org/10.3115/1073336.1073359 . .

C Sporleder , , , A Lascarides . . Using automatically labelled examples to classify rhetorical relations: an assessment . . Nat Lang Eng , , 2008 . . 14 369 - - 416 . . DOI: 10.1017/S1351324906004451 http://doi.org/10.1017/S1351324906004451 . .

S Verberne , , , L Boves , , , N Oostdijk , , , 等 . . Evaluating discourse-based answer extraction for why-question answering . . Proc 30 th Annual Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2007 . . p.735 - - 736 . . DOI: 10.1145/1277741.1277883 http://doi.org/10.1145/1277741.1277883 . .

X Wan . . Co-training for cross-lingual sentiment classification . . Proc of the Joint Conf 47 th Annual Meeting of the ACL and the 4 th Int Joint Conf on Natural Language Processing of the AFNLP , , 2009 . . p.235 - - 243 . . . .

W Wang , , , J Su , , , C Tan . . Kernel based discourse relation recognition with temporal ordering information . . Proc 48 th Annual Meeting of the Association for Computational Linguistics , , 2010 . . p.710 - - 719 . . . .

X Wang , , , S Li , , , J Li , , , 等 . . Implicit discourse relation recognition by selecting typical training examples . . Proc of COLING , , 2012 . . p.2757 - - 2772 . . . .

N Xue . . Annotating discourse connectives in the Chinese treebank . . Proc Workshop on Frontiers in Corpus Annotations Ⅱ: Pie in the Sky , , 2005 . . p.84 - - 91 . . DOI: 10.3115/1608829.1608841 http://doi.org/10.3115/1608829.1608841 . .

B Zhang , , , J Su , , , D Xiong , , , 等 . . Shallow convolutional neural network for implicit discourse relation recognition . . Proc Conf on Empirical Methods in Natural Language Processing , , 2015 . . p.2230 - - 2235 . . DOI: 10.18653/v1/d15-1266 http://doi.org/10.18653/v1/d15-1266 . .

B Zhang , , , D Xiong , , , J Su , , , 等 . . Variational neural discourse relation recognizer . . Proc Conf on Empirical Methods in Natural Language Processing , , 2016 . . p.382 - - 391 . . DOI: 10.18653/v1/d16-1037 http://doi.org/10.18653/v1/d16-1037 . .

M Zhang , , , Y Song , , , B Qin , , , 等 . . Chinese discourse relation recognition . . J Chin Inform Proc , , 2013 . . 27 ( ( 6 ): ): 51 - - 57 . . . .

M Zhang , , , B Qin , , , T Liu . . Chinese discourse relation hierarchy and annotation . . J Chin Inform Proc , , 2014 . . 28 ( ( 2 ): ): 28 - - 36 . . . .

L Zhou , , , W Gao , , , B Li , , , 等 . . Cross-lingual identification of ambiguous discourse connectives for resource poor language . . Proc COLING , , 2012 . . p.1409 - - 1418 . . . .

Y Zhou , , , N Xue . . The Chinese discourse treebank: a Chinese corpus annotated with discourse relations . . Lang Res Eval , , 2015 . . 49 ( ( 2 ): ): 397 - - 431 . . DOI: 10.1007/s10579-014-9290-3 http://doi.org/10.1007/s10579-014-9290-3 . .

Z Zhou , , , Y Xu , , , Z Niu , , , 等 . . Predicting discourse connectives for implicit discourse relation recognition . . 23 rd Int Conf on Computational Linguistics , , 2010 . . p.1507 - - 1514 . . . .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰