反问是现代汉语中一种常用的修辞手法,根据是否含有反问标记可分为显式反问句与隐式反问句。其中隐式反问句表达的情感更为丰富,表现形式也十分复杂,对隐式反问句的识别更具挑战性。该文首先扩充了汉语反问句语料库,语料库规模达到10 000余句,接着针对隐式反问句的特点,提出了一种融合情感分析的隐式反问句识别模型。模型考虑了句子的语义信息、上下文信息,并借助情感分析任务辅助识别隐式反问句。实验结果表明,该文提出的模型在隐式反问句识别任务上取得了良好的性能。
Abstract
Rhetorical question is a commonly used rhetorical technique in modern Chinese. It can be divided into explicit rhetorical questions and implicit rhetorical questions according to whether it contains a rhetorical question mark. The implicit rhetorical question is more complex with rich emotions. This paper first collects a Chinese rhetorical question corpus with more than 10,000 sentences. Then it proposes an implicit rhetorical question recognition model integrated with a sentiment analysis. The model considers the semantic information and context information of the sentence, and introduces the semantic analyss task into identifying implicit rhetorical questions. The experimental results show that the model proposed in this paper achieve good performance on the task of implicit rhetorical question recognition.
关键词
隐式反问句识别 /
情感捕捉 /
上下文信息 /
词性
{{custom_keyword}} /
Key words
implicit rhetorical question detection /
sentiment capture /
contextual information /
POS
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李翔, 朱晓旭, 刘承伟. 面向新闻评论的汉语语料库构建[J]. 山西大学学报, 2021, 44(03): 1-9.
[2] 刘芳. 现代汉语反问句的标记研究[D]. 沈阳: 沈阳师范大学硕士学位论文, 2011.
[3] 殷树林. 现代汉语反问句特有的句法结构[J]. 湖南科技大学学报, 2007, 10(3): 101-105.
[4] 于天昱. 反问句在话语进程中的作用[J]. 广西师范大学学报, 2018, 54(3): 96-102.
[5] 刘钦荣.反问句的句法、语义、语用分析[J].河南师范大学学报, 2004, 31(04): 107-110.
[6] 朱俊雄. 反问句的否定指向[J]. 内江师范学院学报, 2004, 19(5): 38-41.
[7] 刘松江. 反问句的交际作用[J]. 语言教学与研究, 1993,2(47): 46-49.
[8] 王敏. 从语境角度看反问句的识别、理解与翻译: 以《坛经》为例[J]. 开封教育学院学报, 2011, 31(2): 75-78.
[9] 陈海庆, 孙润妤. 庭审语境下被告人反问句多模态语用分析[J]. 天津外国语大学学报, 2020, 27(3): 109-125.
[10] BHATTASALI S, CYTRYN J, FELDMAN E, et al. Automatic identification of rhetorical questions[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing, 2015: 743-749.
[11] RANGANATH S, HU X, TANG J, et al. Identifying rhetorical questions in social media[C]//Proceedings of the International AAAI Conference on Web and Social Media, 2016: 667-670.
[12] ORABY S, HARRISON V, MISRA A, et al. Are you serious?: rhetorical questions and sarcasm in social media dialog[C]//Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue,2017:310-319.
[13] 文治, 李旸, 王素格,等. 融合反问特征的卷积神经网络的中文反问句识别 [J]. 中文信息学报, 2019, 33(1): 68-76.
[14] 李旸, 吴卓嘉, 王素格, 等. 基于语言特征自动获取的反问句识别方法[J]. 中文信息学报, 2020, 34(2): 96-104.
[15] CHO K, VAN M, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of EMNLP,2014:1724-1734.
[16] LECUN Y, BOSER B, DENKER J, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4): 541-551.
[17] LIN Z, FENG M, SANTOS C N, et al. A structured self-attentive sentence embedding[C]//Proceedings of ICLR,2017:1-15.
[18] 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 Association for Computational Linguistics, 2016: 207-212.
[19] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[20] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 6000-6010.
[21] MAJUMDER N, PORIA S, PENG H, et al. Sentiment and sarcasm classification with multitask learning[J]. IEEE Intelligent Systems, 2019, 34(3): 38-43.
[22] SRIVASTAVA H, VARSHNEY V, KUMARI S, et al. A novel hierarchical bert architecture for sarcasm detection[C]//Proceedings of the Workshop on Figurative Language Processing, 2020: 93-97.
[23] DEVLIN J, CHANG M, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 4171-4186.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61836007);江苏高校优势学科建设工程资助项目
{{custom_fund}}
PDF(1478 KB)
