Computer Science

Computer Science ›› 2021, Vol. 48 ›› Issue (10): 85-90.doi: 10.11896/jsjkx.200800115

• Artificial Intelligence • Previous Articles     Next Articles

Chinese Implicit Discourse Relation Recognition Based on Data Augmentation

WANG Ti-shuang, LI Pei-feng, ZHU Qiao-ming   

  1. School of Computer Sciences and Technology,Soochow University,Suzhou,Jiangsu 215006,China
    Provincial Key Laboratory for Computer Information Processing Technology,Suzhou,Jiangsu 215006,China
  • Received:2020-08-18 Revised:2021-01-21 Online:2021-10-15 Published:2021-10-18
  • About author:WANG Ti-shuang,born in 1993.His main research interests include natural language processing and machine lear-ning.
    LI Pei-feng,born in 1971,Ph.D,professor,Ph.D supervisor,is a member of China Computer Federation.His main research interests include natural language processing and machine learning.
  • Supported by:
    National Natural Science Foundation of China(61836007,61772354,61751206) and Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD).

PDF (PC)

876

Abstract: Due to the lack of connectives,implicit discourse relation recognition is a challenging task,especially in Chinese.This paper proposes a method for Chinese implicit discourse relation recognition,which expands the training data by combining active learning and multi-task learning method.This method aims to reduce the noise as much as possible when it expands the training data set.Firstly,the active learning is used to select some explicit data through the classification uncertainty based on BERT,and then the connectives in the explicit data are removed and regarded as pseudo-implicit training data.Finally,a multi task learning method is used to boost implicit discourse relation recognition by using the pseudo-implicit training data.Experimental results on Chinese discourse treebank (CDTB) show that our method improves the macro-average F1 and micro-average F1 scores,compared with the baselines.

Key words: Active learning, Discourse parsing, Implicit discourse relation recognition, Multi-task learning

CLC Number: 

  • TP391
[1]LIAKATA M,DOBNIK S,SAHA S,et al.A discourse-driven content model for summarising scientific articles evaluated in a complex question answering task [C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Proces-sing.2013:747-757.
[2]TU M,ZHOU Y,ZONG G.Enhancing grammatical cohesion:Generating transitional expressions for SMT[C]//Proceedings of the 52nd Annual Meeting of the Association for Computatio-nal Linguistics.2014:850-860.
[3]XUE N,TOU H,PRADHAN S.The CoNLL-2016 shared task on shallow discourse parsing[C]//Proceedings of the 20th Conference on Computational Natural Language Learning-Shared Task.2016:1-19.
[4]PILER E,LOUIS A,NENKOVA A.Autimatic sense prediction for implicit discourse relation in text[C]//Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP.2009:683-691.
[5]CHEN J,ZHANG Q,LIU P.Implicit Discourse Relation Detection via a Deep Architecture with Gated Relevance Network[C]//Proceedings of the 54nd Annual Meeting of the Association for Computational Linguistics.2016:1726-1735.
[6]LIU Y,LI S.Recognizing Implicit Discourse Relations via Re-peated Reading Neural Networks with Multi-Level Attention Building Chinese discourse corpus with connective-driven dependency tree structure[C]//Proceedings of the 2016 Confe-rence on Empirical Methods in Natural Language Processing.2016:1224-1233.
[7]JIA Y,YE Y,FENG Y,et al.Modeling discourse cohesion for discourse parsing via memory network[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.2018:438-443.
[8]NGUYEN L T,NGO L U,THAN K,et al.Employing the Correspondence of Relations and Connectives to Identify Implicit Discourse Relations via Label Embeddings[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.2019:4201-4207.
[9]XU Y,HONG Y,RUAN H,et al.Using Active Learning to Expand Training Data for Implicit Discourse Relation Recognition[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.2018:725-731.
[10]LIU Y,LI S,ZHANG X.Implicit Discourse Relation Classification via Multi-task Neural Networks[C]//Proceedings of the 2016 AAAI Conference on Artificial Intelligence.2016:2750-2756.
[11]LI Y,KONG F,ZHOU G.Building Chinese discourse corpuswith connective-driven dependency tree structure[C]//In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing.2014:2105-2114.
[12]CARLSON L,OKUROWSKI M E,MARCU D.RST discourse treebank[M].Linguistic Data Consortium,University of Pennsylvania,2002.
[13]RASHMI P,ELENI M,NIKHIL D,et al.The Penn Discourse Treebank 2.0 Annotation Manual[OL].https://www.seas.upenn.edu/~pdtb/PDTBAPI/pdtb-annotation-manual.pdf.
[14]KONG F,ZHOU G.A CDT-styled end-to-end Chinese discourse parser[J].ACM Transactions on Asian and Low-Resource Language Information Processing,2017,16(4):26.
[15]XU S,WANG T S,LI P F,et al.Multi-Layer Attention Network Based Chinese Implicit Discourse Relation Recognition[J].Journal of Chinese Information Processing,2019,27(3):12-19.
[16]XU S,LI P,ZHU Q,et al.Topic tensor network for implicit discourse relation recognition in Chinese[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.2019:608-618.
[17]SPORLEDER C,LASCARIDES A.Using Automatically La-belled Examples to Classify Rhetorical Relations:an Assessment[J].Natural Language Engineering,2008,14(3):369-416.
[18]DEVLIN J,CHANG M,LEE K,et al.BERT:Pre-training of Deep Bidirectional Transformers for Language Understanding[J].arXiv:1810.04805.
[19]MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed representations of words and phrases and their compositionality[C]//Advances in Neural Information Processing Systems.2013:3111-3119.
[20]SELLTES B.Active Learning Literature Survey[R].Computer Sciences Technical Report,University of Wisconsin-Madison,2009.
[21]RAMIREZ-LOAIZA M E,SHARMA M,KUMAR G,et al.Active learning:an empirical study of common baselines[J].Data Mining and Knowledge Discovery.2017,31(2):287-313.
[22]XUE N,XIA F,CHIOU F,et al.The Penn Chinese treebank:Phrase structure annotation of a large corpus[J].Natural Language Engineering,2005,11(2):207-238.
[23]HINTON G E,SRIVASTAVA N,KRIZHEVSKY A,et al.Improving neural networks by preventing co-adaptation of feature detectors[J].arXiv:1207.0580,2012.
[1] ZHOU Hui, SHI Hao-chen, TU Yao-feng, HUANG Sheng-jun. Robust Deep Neural Network Learning Based on Active Sampling [J]. Computer Science, 2022, 49(7): 164-169.
[2] DU Li-jun, TANG Xi-lu, ZHOU Jiao, CHEN Yu-lan, CHENG Jian. Alzheimer's Disease Classification Method Based on Attention Mechanism and Multi-task Learning [J]. Computer Science, 2022, 49(6A): 60-65.
[3] HOU Xia-ye, CHEN Hai-yan, ZHANG Bing, YUAN Li-gang, JIA Yi-zhen. Active Metric Learning Based on Support Vector Machines [J]. Computer Science, 2022, 49(6A): 113-118.
[4] ZHAO Kai, AN Wei-chao, ZHANG Xiao-yu, WANG Bin, ZHANG Shan, XIANG Jie. Intracerebral Hemorrhage Image Segmentation and Classification Based on Multi-taskLearning of Shared Shallow Parameters [J]. Computer Science, 2022, 49(4): 203-208.
[5] YANG Xiao-yu, YIN Kang-ning, HOU Shao-qi, DU Wen-yi, YIN Guang-qiang. Person Re-identification Based on Feature Location and Fusion [J]. Computer Science, 2022, 49(3): 170-178.
[6] SONG Long-ze, WAN Huai-yu, GUO Sheng-nan, LIN You-fang. Multi-task Spatial-Temporal Graph Convolutional Network for Taxi Idle Time Prediction [J]. Computer Science, 2021, 48(7): 112-117.
[7] LIU Xiao-long, HAN Fang, WANG Zhi-jie. Joint Question Answering Model Based on Knowledge Representation [J]. Computer Science, 2021, 48(6): 241-245.
[8] ZHANG Ren-zhi, ZHU Yan. Malicious User Detection Method for Social Network Based on Active Learning [J]. Computer Science, 2021, 48(6): 332-337.
[9] ZHOU Xiao-jin, XU Chen-ming, RUAN Tong. Multi-granularity Medical Entity Recognition for Chinese Electronic Medical Records [J]. Computer Science, 2021, 48(4): 237-242.
[10] ZHANG Chun-yun, QU Hao, CUI Chao-ran, SUN Hao-liang, YIN Yi-long. Process Supervision Based Sequence Multi-task Method for Legal Judgement Prediction [J]. Computer Science, 2021, 48(3): 227-232.
[11] YU Liang, WEI Yong-feng, LUO Guo-liang, WU Chang-xing. Knowledge Distillation Based Implicit Discourse Relation Recognition [J]. Computer Science, 2021, 48(11): 319-326.
[12] PAN Zu-jiang, LIU Ning, ZHANG Wei, WANG Jian-yong. MTHAM:Multitask Disease Progression Modeling Based on Hierarchical Attention Mechanism [J]. Computer Science, 2020, 47(9): 185-189.
[13] DONG Xin-yue, FAN Rui-dong, HOU Chen-ping. Active Label Distribution Learning Based on Marginal Probability Distribution Matching [J]. Computer Science, 2020, 47(9): 190-197.
[14] HU Chao-wen, YANG Ya-lian, WU Chang-xing. Survey of Implicit Discourse Relation Recognition Based on Deep Learning [J]. Computer Science, 2020, 47(4): 157-163.
[15] ZHOU Zi-qin, YAN Hua. 3D Shape Recognition Based on Multi-task Learning with Limited Multi-view Data [J]. Computer Science, 2020, 47(4): 125-130.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.