计算机科学 ›› 2021, Vol. 48 ›› Issue (10): 85-90.doi: 10.11896/jsjkx.200800115
王体爽, 李培峰, 朱巧明
WANG Ti-shuang, LI Pei-feng, ZHU Qiao-ming
摘要: 由于缺乏显式连接词,隐式篇章关系识别是一个具有挑战性的任务。文中提出了一种结合主动学习和多任务学习来间接扩充隐式篇章关系训练数据的隐式篇章关系识别方法,旨在在增强训练数据的同时尽量少地引入伪隐式篇章关系数据中的噪声。首先,基于BERT模型通过主动学习方法的分类不确定性来选择部分显式篇章关系样本;然后,移除显式篇章关系数据中的显式连接词作为伪隐式篇章关系数据;最后,采用多任务学习方法使伪隐式篇章关系数据有助于隐式篇章关系识别。在中文篇章树库(CDTB)上进行的实验的结果显示,相比基准模型,所提方法在宏平均F1、微平均F1值上均得到了提高。
中图分类号:
[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] | 周慧, 施皓晨, 屠要峰, 黄圣君. 基于主动采样的深度鲁棒神经网络学习 Robust Deep Neural Network Learning Based on Active Sampling 计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044 |
[2] | 杜丽君, 唐玺璐, 周娇, 陈玉兰, 程建. 基于注意力机制和多任务学习的阿尔茨海默症分类 Alzheimer's Disease Classification Method Based on Attention Mechanism and Multi-task Learning 计算机科学, 2022, 49(6A): 60-65. https://doi.org/10.11896/jsjkx.201200072 |
[3] | 侯夏晔, 陈海燕, 张兵, 袁立罡, 贾亦真. 一种基于支持向量机的主动度量学习算法 Active Metric Learning Based on Support Vector Machines 计算机科学, 2022, 49(6A): 113-118. https://doi.org/10.11896/jsjkx.210500034 |
[4] | 赵凯, 安卫超, 张晓宇, 王彬, 张杉, 相洁. 共享浅层参数多任务学习的脑出血图像分割与分类 Intracerebral Hemorrhage Image Segmentation and Classification Based on Multi-taskLearning of Shared Shallow Parameters 计算机科学, 2022, 49(4): 203-208. https://doi.org/10.11896/jsjkx.201000153 |
[5] | 杨晓宇, 殷康宁, 候少麒, 杜文仪, 殷光强. 基于特征定位与融合的行人重识别算法 Person Re-identification Based on Feature Location and Fusion 计算机科学, 2022, 49(3): 170-178. https://doi.org/10.11896/jsjkx.210100132 |
[6] | 宋龙泽, 万怀宇, 郭晟楠, 林友芳. 面向出租车空载时间预测的多任务时空图卷积网络 Multi-task Spatial-Temporal Graph Convolutional Network for Taxi Idle Time Prediction 计算机科学, 2021, 48(7): 112-117. https://doi.org/10.11896/jsjkx.201000089 |
[7] | 郭文, 尹童灵, 张天柱, 徐常胜. 时间一致性保持的多任务稀疏深度表达视觉跟踪 Temporal Consistency Preserving Multi-Mask Sparse Deep Representation for Visual Tracking 计算机科学, 2021, 48(6): 110-117. https://doi.org/10.11896/jsjkx.200800212 |
[8] | 刘小龙, 韩芳, 王直杰. 基于知识表示的联合问答模型 Joint Question Answering Model Based on Knowledge Representation 计算机科学, 2021, 48(6): 241-245. https://doi.org/10.11896/jsjkx.200600011 |
[9] | 张人之, 朱焱. 基于主动学习的社交网络恶意用户检测方法 Malicious User Detection Method for Social Network Based on Active Learning 计算机科学, 2021, 48(6): 332-337. https://doi.org/10.11896/jsjkx.200700151 |
[10] | 周晓进, 徐陈铭, 阮彤. 面向中文电子病历的多粒度医疗实体识别 Multi-granularity Medical Entity Recognition for Chinese Electronic Medical Records 计算机科学, 2021, 48(4): 237-242. https://doi.org/10.11896/jsjkx.200100036 |
[11] | 张春云, 曲浩, 崔超然, 孙皓亮, 尹义龙. 基于过程监督的序列多任务法律判决预测方法 Process Supervision Based Sequence Multi-task Method for Legal Judgement Prediction 计算机科学, 2021, 48(3): 227-232. https://doi.org/10.11896/jsjkx.200700056 |
[12] | 俞亮, 魏永丰, 罗国亮, 邬昌兴. 基于知识蒸馏的隐式篇章关系识别 Knowledge Distillation Based Implicit Discourse Relation Recognition 计算机科学, 2021, 48(11): 319-326. https://doi.org/10.11896/jsjkx.201000099 |
[13] | 潘祖江, 刘宁, 张伟, 王建勇. 基于层次注意力机制的多任务疾病进展模型 MTHAM:Multitask Disease Progression Modeling Based on Hierarchical Attention Mechanism 计算机科学, 2020, 47(9): 185-189. https://doi.org/10.11896/jsjkx.190900001 |
[14] | 董心悦, 范瑞东, 侯臣平. 基于边际概率分布匹配的主动标记分布学习 Active Label Distribution Learning Based on Marginal Probability Distribution Matching 计算机科学, 2020, 47(9): 190-197. https://doi.org/10.11896/jsjkx.200700077 |
[15] | 周子钦, 严华. 基于多任务学习的有限样本多视角三维形状识别算法 3D Shape Recognition Based on Multi-task Learning with Limited Multi-view Data 计算机科学, 2020, 47(4): 125-130. https://doi.org/10.11896/jsjkx.190700163 |
|