融合特征编码和短语交互感知的隐式篇章关系识别

王秀利; 金方焱

doi:10.12263/DZXB.20220246

您当前的位置：

首页 >

文章列表页 >

融合特征编码和短语交互感知的隐式篇章关系识别

学术论文 | 更新时间：2025-12-08

- 融合特征编码和短语交互感知的隐式篇章关系识别
- Implicit Discourse Relation Recognition Integrating Feature Coding and Phrase Interaction Perception
- 电子学报 2024年52卷第4期页码：1377-1388
- 作者机构：
  
  1.中央财经大学信息学院，北京102206
  2.国家金融安全教育部工程研究中心，北京102206
- 作者简介：
  
  [ "王秀利男，中央财经大学信息学院/国家金融安全教育部工程研究中心教授，博士生导师.主要研究方向为金融科技与安全，大数据与人工智能.E-mail： wangcufe@163.com" ]
  [ "金方焱男，中央财经大学信息学院硕士研究生.主要研究方向为自然语言处理." ]
- 基金信息：
  
  教育部哲学社会科学研究重大课题攻关项目(22JZD011);中央财经大学新兴交叉学科建设项目
- DOI：10.12263/DZXB.20220246
  中图分类号： TP391;
- 收稿：2022-03-09，
  
  修回：2022-09-14，
  
  纸质出版：2024-04-25
- 稿件说明：
移动端阅览
王秀利, 金方焱. 融合特征编码和短语交互感知的隐式篇章关系识别[J]. 电子学报, 2024, 52(04): 1377-1388.

WANG Xiu-li, JIN Fang-yan. Implicit Discourse Relation Recognition Integrating Feature Coding and Phrase Interaction Perception[J]. Acta Electronica Sinica, 2024, 52(04): 1377-1388.
王秀利, 金方焱. 融合特征编码和短语交互感知的隐式篇章关系识别[J]. 电子学报, 2024, 52(04): 1377-1388. DOI：10.12263/DZXB.20220246

WANG Xiu-li, JIN Fang-yan. Implicit Discourse Relation Recognition Integrating Feature Coding and Phrase Interaction Perception[J]. Acta Electronica Sinica, 2024, 52(04): 1377-1388. DOI：10.12263/DZXB.20220246

摘要

隐式篇章关系识别难度大、普遍性高.从论元编码和论元交互角度入手，提出了一种融合特征编码和短语交互感知的隐式篇章关系识别模型.该模型兼顾了论元本身特征和论元间交互特征的作用，并分别进行了优化.论元编码部分整合了双向长短时记忆网络和循环注意力卷积神经网络，能够更全面地捕获论元全局和局部特征；论元交互部分从短语层级考虑论元间的语义关系建模，构建了短语级交互注意力机制，并利用神经张量网络深入挖掘其中的关系模式，更能体现出论元间潜在的更深层次的关联关系.在宾州篇章树库数据集上的实验结果表明，该模型

值均优于其他模型.

Abstract

Implicit discourse relation recognition is a challenging task because of its difficulty and universality. From the perspective of argument coding and argument interaction

an implicit discourse relation recognition model integrating feature coding and phrase interaction perception is proposed. The model considers both the characteristics of argument itself and the interaction characteristics between arguments

and optimizes separately. The part of argument coding incorporates bidirectional long short-term memory (BiLSTM) and recurrent attention convolution neural network (RACNN)

which can capture global and local features of arguments in a more comprehensive way; in the part of argument interaction

the semantic relationship between arguments is modeled from phrase level

and a mechanism of phrase-level interactive attention is constructed. Also

neural tensor network (NTN) is used to dig into the relational pattern

which can better reflect the potential deeper relational relationship between arguments. Experimental results on penn discourse treebank (PDTB) dataset show that the

values of this model are superior to other comparison models.

关键词

Keywords

references

ZHOU P , SHI W , TIAN J , et al . Attention-based bidirectional long short-term memory networks for relation classification [C ] // Proceedings of the Annual Meeting of the ACL . Stroudsburg : ACL , 2016 : 207 - 212 .

李志欣 , 孙亚茹 , 唐素勤 , 等 . 双路注意力引导图卷积网络的关系抽取 [J ] . 电子学报 , 2021 , 49 ( 2 ): 315 - 323 .

LI Z X , SUN Y R , TANG S Q , et al . Dual attention guided graph convolutional networks for relation extraction [J ] . Acta Electronica Sinica , 2021 , 49 ( 2 ): 315 - 323 . (in Chinese)

ZHANG Y , MENG F , LI P , et al . Context tracking network: Graph-based context modeling for implicit discourse relation recognition [C ] // Proceedings of the Conference of the North American Chapter of the ACL: Human Language Technologies . Stroudsburg : ACL , 2021 : 1592 - 1599 .

WU W , WANG H , LIU T , et al . Phrase-level self-attention networks for universal sentence encoding [C ] // Proceedings of the Conference on Empirical Methods in Natural Language Processing . Stroudsburg : ACL , 2018 : 3729 - 3738 .

ZHANG B , SU J , XIONG D , et al . Shallow convolutional neural network for implicit discourse relation recognition [C ] // Proceedings of the Conference on Empirical Methods in Natural Language Processing . Stroudsburg : ACL , 2015 : 2230 - 2235 .

RUTHERFORD A , DEMBERG V , XUE N . A systematic study of neural discourse models for implicit discourse relation [C ] // Proceedings of the Conference of the European Chapter of the ACL . Stroudsburg : ACL , 2017 : 281 - 291 .

凡子威 , 张民 , 李正华 . 基于BiLSTM并结合自注意力机制和句法信息的隐式篇章关系分类 [J ] . 计算机科学 , 2019 , 46 ( 5 ): 214 - 220 .

FAN Z W , ZHANG M , LI Z H . BiLSTM-based implicit discourse relation classification combining self-attention mechanism and syntactic information [J ] . Computer Science , 2019 , 46 ( 5 ): 214 - 220 . (in Chinese)

DAI Z , HUANG R . Improving implicit discourse relation classification by modeling inter-dependencies of discourse units in a paragraph [C ] // Proceedings of the Conference of the North American Chapter of the ACL: Human Language Technologies . Stroudsburg : ACL , 2018 : 141 - 151 .

ZHANG B , XIONG D , SU J , et al . Learning better discourse representation for implicit discourse relation recognition via attention networks [J ] . Neurocomputing , 2018 , 275 : 1241 - 1249 .

POPA D N , PEREZ J , HENDERSON J , et al . Implicit discourse relation classification with syntax-aware contextualized word representations [C ] // Proceedings of the Florida Artificial Intelligence Research Society . New York : AAAI , 2019 : 203 - 208 .

GUO F , HE R , DANG J . Implicit discourse relation recognition via a BiLSTM-CNN architecture with dynamic chunk-based max pooling [J ] . IEEE Access , 2019 , 7 : 169281 - 169292 .

徐扬 , 周文瑄 , 阮慧彬 , 等 . 基于层次化表示的隐式篇章关系识别 [J ] . 南京大学学报: 自然科学版 , 2019 , 55 ( 6 ): 1000 - 1009 .

XU Y , ZHOU W X , RUAN H B , et al . Hierarchical representation for implicit discourse relation recognition [J ] . Journal of Nanjing University (Natural Sciences) , 2019 , 55 ( 6 ): 1000 - 1009 . (in Chinese)

阮慧彬 , 徐扬 , 孙雨 , 等 . 基于堆叠式注意力机制的隐式篇章关系识别 [J ] . 山西大学学报: 自然科学版 , 2020 , 43 ( 3 ): 508 - 516 .

RUAN H B , XU Y , SUN Y , et al . Stacked-attention based implicit discourse relation recognition [J ] . Journal of Shanxi University (Natural Sciences) , 2020 , 43 ( 3 ): 508 - 516 . (in Chinese)

GUO F , HE R , JIN D , et al . Implicit discourse relation recognition using neural tensor network with interactive attention and sparse learning [C ] // Proceedings of the Conference on Computational Linguistics . Stroudsburg : ACL , 2018 : 547 - 558 .

徐昇 , 王体爽 , 李培峰 , 等 . 运用多层注意力神经网络识别中文隐式篇章关系 [J ] . 中文信息学报 , 2019 , 33 ( 8 ): 12 - 19, 35 .

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 , 33 ( 8 ): 12 - 19, 35 . (in Chinese)

LIU X , OU J , SONG Y , et al . On the importance of word and sentence representation learning in implicit discourse relation classification [C ] // Proceedings of the Conference on Artificial Intelligence . Amsterdam : Elsevier , 2020 : 3830 - 3836 .

HE R , WANG J , GUO F , et al . Transs-driven joint learning architecture for implicit discourse relation recognition [C ] // Proceedigns of the Annual Meeting of the ACL . Stroudsburg : ACL , 2020 : 139 - 148 .

BAI H , ZHAO H . Deep enhanced representation for implicit discourse relation recognition [C ] // Proceedings of the Conference on Computational Linguistics . Stroudsburg : ACL , 2018 : 571 - 583 .

唐裕婷 , 李艳斌 , 刘露 , 等 . 面向细粒度隐式篇章关系识别的远距离监督特征学习算法 [J ] . 北京大学学报: 自然科学版 , 2019 , 55 ( 1 ): 91 - 97 .

TANG Y T , LI Y B , LIU L , et al . Feature learning by distant supervision for fine-grained implicit discourse relation identification [J ] . Acta Scientiarum Naturalium Universitatis Pekinensis , 2019 , 55 ( 1 ): 91 - 97 . (in Chinese)

GUO F , HE R , DANG J , et al . Working memory-driven neural networks with a novel knowledge enhancement paradigm for implicit discourse relation recognition [C ] // Proceedings of the Conference on Artificial Intelligence . New York : AAAI , 2020 : 7822 - 7829 .

KURFALI M , ÖSTLING R . Let's be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction [C ] // Proceedings of the Workshop on Understanding Implicit and Underspecified Language . Stroudsburg : ACL , 2021 : 1 - 10 .

FU J L , ZHENG H L , MEI T . Look closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition [C ] // Proceedings of the Conference on CVPR . Piscataway : IEEE , 2017 : 4476 - 4484 .

PRASAD R , DINESH N , LEE A , et al . The penn discourse treebank 2.0 [C ] // Proceedings of the Conference on Language Resources and Evaluation . Marrakech : LREC , 2008 : 2961 - 2968 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

融合特征编码和短语交互感知的隐式篇章关系识别

基于双路分段注意力神经张量网络的临床文本关系抽取

衰减解耦机制的图像分类网络

基于改进Res2Net与自适应多尺度窗口池化的调制识别方法

基于自适应群体掩码图卷积网络的行人轨迹预测