基于句子关联图的汉越双语多文档新闻观点句识别

doi:10.11772/j.issn.1001-9081.2020020280

计算机应用 ›› 2020, Vol. 40 ›› Issue (10): 2845-2849.DOI: 10.11772/j.issn.1001-9081.2020020280

基于句子关联图的汉越双语多文档新闻观点句识别

王剑^1,2, 唐珊^1,2, 黄于欣^1,2, 余正涛^1,2

1. 昆明理工大学信息工程与自动化学院, 昆明 650500;
2. 云南省人工智能重点实验室(昆明理工大学), 昆明 650500

收稿日期:2020-03-14 修回日期:2020-04-22 发布日期:2020-05-18 出版日期:2020-10-10
通讯作者: 余正涛
作者简介:王剑(1976-),男,浙江长兴人,副教授,硕士,主要研究方向:自然语言处理、机器学习、软件过程与演化;唐珊(1993-),女,辽宁义县人,硕士研究生,主要研究方向:自然语言处理、跨语言情感分析;黄于欣(1983-),男,河南洛阳人,博士研究生,CCF会员,主要研究方向:自然语言处理、文本摘要;余正涛(1970-),男,云南曲靖人,教授,博士,CCF会员,主要研究方向:自然语言处理、机器翻译、信息检索。
基金资助:
国家自然科学基金资助项目（61972186，61762056，61472168）；云南省高新技术产业专项（201606）。

Chinese-Vietnamese bilingual multi-document news opinion sentence recognition based on sentence association graph

WANG Jian^1,2, TANG Shan^1,2, HUANG Yuxin^1,2, YU Zhengtao^1,2

1. Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming Yunnan 650500, China;
2. Yunnan Key Laboratory of Artificial Intelligence(Kunming University of Science and Technology), Kunming Yunnan 650500, China

Received:2020-03-14 Revised:2020-04-22 Online:2020-05-18 Published:2020-10-10
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61972186, 61762056, 61472168), the High-tech Industry Special Project of Yunnan (201606).

摘要/Abstract

摘要： 传统的观点句识别多利用句子内部的情感特征进行分类，而在跨语言的多文档观点句识别任务中，不同语言、不同文档的句子之间具有密切的关联，这些关联特征对于观点句识别有一定的支撑作用。因此，提出一种基于双向长短期记忆（Bi-LSTM）网络框架并融入句子关联特征的汉越双语多文档新闻观点句识别方法。首先提取汉越双语句子的情感要素和事件要素，构建句子关联图，并利用TextRank算法得到句子关联特征；然后基于双语词嵌入和Bi-LSTM将汉语和越语的新闻文本编码在同一个语义空间；最后联合考虑句子编码特征和关联特征进行观点句识别。理论分析和模拟结果表明，融入句子关联图能够有效地提升多文档观点句识别的准确率。

关键词: 汉越双语新闻, 观点句识别, 句子关联图, 事件要素, 情感要素

Abstract: The traditional opinion sentence recognition tasks mainly realize the classification by emotional features inside the sentence. In the task of cross-lingual multi-document opinion sentence recognition, the certain supporting function for opinion sentence recognition was provided by the association between sentences in different languages and documents. Therefore, a Chinese-Vietnamese bilingual multi-document news opinion sentence recognition method was proposed by combining Bi-directional Long Short Term Memory (Bi-LSTM) network framework and sentence association features. Firstly, emotional elements and event elements were extracted from the Chinese-Vietnamese bilingual sentences to construct the sentence association diagram, and the sentence association features were obtained by using TextRank algorithm. Secondly, the Chinese and Vietnamese news texts were encoded in the same semantic space based on the bilingual word embedding and Bi-LSTM. Finally, the opinion sentence recognition was realized by jointly considering the sentence coding features and semantic features. The theoretical analysis and simulation results show that integrating sentence association diagram can effectively improve the precision of multi-document opinion sentence recognition.

Key words: Chinese-Vietnamese bilingual news, opinion sentence recognition, sentence association diagram, event element, emotional element

中图分类号:

TP391

王剑, 唐珊, 黄于欣, 余正涛. 基于句子关联图的汉越双语多文档新闻观点句识别[J]. 计算机应用, 2020, 40(10): 2845-2849.

WANG Jian, TANG Shan, HUANG Yuxin, YU Zhengtao. Chinese-Vietnamese bilingual multi-document news opinion sentence recognition based on sentence association graph[J]. Journal of Computer Applications, 2020, 40(10): 2845-2849.

参考文献

[1] KIM S M,HOVY E. Determining the sentiment of opinions[C]//Proceedings of the 20th International Conference on Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics,2004:1367-1373.
[2] MIHALCEA R, BANEA C, WIEBE J. Learning multilingual subjective language via cross-lingual projections[C]//Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics,2007:976-983.
[3] 刘培玉, 荀静, 费绍栋, 等. 基于隐马尔可夫模型的主观句识别[J]. 中文信息学报,2016,30(4):206-212.(LIU P Y,XUN J, FEI S D,et al. Subjective sentence recognition based on hidden Markov model[J]. Journal of Chinese Information Processing, 2016,30(4):206-212.)
[4] ALMEIDA M S C,PINTO C,FIGUEIRA H,et al. Aligning opinions:cross-lingual opinion mining with dependencies[C]//Proceeding of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Stroudsburg,PA:Association for Computational Linguistics,2015:408-418.
[5] BANEA C, MIHALCEA R, WIEBE J. Porting multilingual subjectivity resources across languages[J]. IEEE Transactions on Affective Computing,2013,4(2):211-225.
[6] BANEA C, MIHALCEA R, WIEBE J, et al. Multilingual subjectivity analysis using machine translation[C]//Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics,2008:127-135.
[7] ZHOU X,WAN X,XIAO J. Attention-based LSTM network for cross-lingual sentiment classification[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics, 2016:247-256.
[8] ZHOU X,WAN X,XIAO J. Cross-lingual sentiment classification with bilingual document representation learning[C]//Proceeding of the 54th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics,2016:1403-1412.
[9] ZHOU H,YANG Y,LIU Z,et al. Jointly learning bilingual sentiment and semantic representation for cross-language sentiment classification[C]//Proceedings of the 23rd China Conference on Information Retrieval, LNCS 10390. Cham:Springer, 2017:149-160.
[10] 林思琦, 余正涛, 郭军军, 等. 融入多特征的汉越新闻观点句抽取方法[J]. 中文信息学报,2019,33(11):101-106.(LIN S Q, YU Z T,GUO J J,et al. Chinese-Vietnamese news perspective sentence extraction methods incorporating multiple features[J]. Journal of Chinese Information Processing, 2019, 33(11):101-106.)
[11] 刘书龙. 汉越双语新闻观点句抽取及分析方法研究[D]. 昆明:昆明理工大学,2017:13-17.(LIU S L. Research on the analysis method of Chinese-Vietnamese bilingual news opinion sentences extraction[D]. Kunming:Kunming University of Science and Technology,2017:13-17.)
[12] MAYFIELD E. Sentence diagram generation using dependency parsing[C]//Proceedings of the ACL-IJCNLP 2009 Student Research Workshop. Stroudsburg, PA:Association for Computational Linguistics,2009:45-53.
[13] HOCHREITER S,SCHMIDHUBER J. LSTM can solve hard long time lag problems[C]//Proceedings of the 9th International Conference on Neural Information Processing Systems. Cambridge:MIT Press,1996:473-479.
[14] MIHALCEA R,TARAU P. TextRank:bringing order into texts[C]//Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing. Stroudsburg,PA:Association for Computational Linguistics,2004:404-411.
[15] KU L W,CHEN H H. Mining opinions from the Web:Beyond relevance retrieval[J]. Journal of the American Society for Information Science and Technology,2007,58(12):1838-1850.

基于句子关联图的汉越双语多文档新闻观点句识别

Chinese-Vietnamese bilingual multi-document news opinion sentence recognition based on sentence association graph

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李强白少雄熊源袁薇. 基于视觉大模型隐私保护的监控图像定位[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[2]	薛雅丽徐忠敏刘世豪. 基于多级小波残差网络的重力数据去噪方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[3]	况世雄姚俊波陆佳炜王琪冰肖刚. 基于动态图卷积网络的电梯乘客异常行为数据增强方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[4]	康斌陈斌王俊杰李昱林赵军智咸伟志. 基于多粒度共享语义中心关联的文本到人物检索方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[5]	张庆杨凡方宇涵. 基于多模态信息融合的中文拼写纠错算法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[6]	王昊王金伟程鑫张家伟吴昊罗向阳马宾. 彩色图像JPEG重压缩取证综述（ChinaMFS 2024+14）[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[7]	王磊胡节彭博. 用于半监督火灾检测的分布自适应和动态课程伪标签框架[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[8]	刘晋文王磊马博董瑞杨雅婷艾合塔木江·艾合麦提王欣乐. 基于弱监督模态语义增强的多模态有害信息检测方法 [J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[9]	夏雨禾王晓东何启学. 基于频域增强图变分学习的时间序列异常检测[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[10]	殷兵, 凌震华, 林垠, 奚昌凤, 刘颖. 兼容缺失模态推理的情感识别方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[11]	王子怡李卫军刘雪洋丁建平刘世侠苏易礌. 基于Swin Transformer与多尺度特征融合的图像描述方法#br# [J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[12]	庞玉东, 李志星, 刘伟杰, 李天昊, 王宁宁. 基于改进实时检测Transformer的塔机上俯视场景小目标检测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3922-3929.
[13]	何长久, 杨婧涵, 周丕宇, 边昕烨, 吕明明, 董迪, 付岩, 王海鹏. 基于Transformer和门控循环单元的肽序列理论串联质谱图预测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3958-3964.
[14]	赵欣, 李鑫杰, 徐健, 刘步云, 毕祥. 基于卷积神经网络与Transformer并行的医学图像配准模型[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3915-3921.
[15]	熊炜, 陈奕博, 张丽真, 杨茜, 邹勤. 利用多帧序列影像的自监督单目深度估计[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3907-3914.