基于扩展的S-LSTM的文本蕴含识别

胡超文; 邬昌兴; 杨亚连

doi:10.7544/issn1000-1239.2020.20190522

基于扩展的S-LSTM的文本蕴含识别

(华东交通大学软件学院南昌 330013) (hcwjuly@126.com)

基金项目: 国家自然科学基金项目(61866012)；江西省自然科学基金项目(20181BAB202012)；江西省教育厅科学技术研究项目(GJJ180329)

详细信息

中图分类号: TP391
计量
- 文章访问数: 1176
- HTML全文浏览量: 3
- PDF下载量: 344
出版历程
- 发布日期: 2020-06-30

Extended S-LSTM Based Textual Entailment Recognition

(School of Software, East China Jiaotong University, Nanchang 330013)

Funds: This work was supported by the National Natural Science Foundation of China (61866012), the Natural Science Foundation of Jiangxi Province of China (20181BAB202012), and the Science and Technology Research Project of Jiangxi Provincial Education Department (GJJ180329).

摘要

摘要: 文本蕴含识别旨在自动判断给定的前提和假设(通常为2个句子)之间是否存在蕴含关系，是自然语言处理领域一项基础但富有挑战的任务.当前，主流的基于深度学习的模型通常分别建模前提和假设的语义表示，而没有把它们看作一个整体；另外，在捕获它们之间的语义关系时，大都没有同时利用句子级别的全局信息和短语级别的局部信息.最近提出的S-LSTM能够同时学习句子和短语的语义表示，在文本分类等任务上取得了较好的效果.基于上述情况，提出了一种基于扩展的S-LSTM的文本蕴含识别模型.一方面，把前提和假设看作一个整体，扩展S-LSTM以同时学习它们的语义表示；另一方面，在建模语义关系时，既利用句子级别的信息又利用短语级别的信息，以此获得更好的语义表示.在英文SNLI数据集和中文CNLI数据集上的实验结果表明：提出的模型取得了比基准模型更好的识别性能.
- 文本蕴含识别 /
- 蕴含关系 /
- 语义关系 /
- 扩展的S-LSTM /
- 深度学习
Abstract: Text entailment recognition aims at automatically determining whether there is an entailment relationship between the given premise and hypothesis (usually two sentences). It is a basic and challenging task in natural language processing. Current dominant models, which are based on deep learning, usually encode the semantic representations of two sentences separately, instead of considering them as a whole. Besides, most of them do not leverage both the sentence-level global and ngram-level local information when capturing the semantic relationship. The recently proposed S-LSTM can learn semantic representations of a sentence and its ngrams simultaneously, achieving promising performance on tasks such as text classification. Considering the above, a model based on an extended S-LSTM is proposed for textual entailment recognition. On the one hand, S-LSTM is extended to learn semantic representations of the premise and hypothesis simultaneously, which regards them as a whole. On the other hand, to obtain better semantic representation, both the sentence-level and ngram-level information are used to capture the semantic relationships. Experimental results, on the English SNLI dataset and Chinese CNLI dataset, show that the performance of the proposed model is better than baselines.
- textual entailment recognition /
- entailment relationship /
- semantic relationship /
- extended S-LSTM /
- deep learning

HTML全文

参考文献(0)

施引文献(21)

期刊类型引用(7)

1.	李皎，张秀山，宁远航. 降低跨分片交易比例的区块链分片方法. 计算机应用. 2024(06): 1889-1896 . 百度学术
2.	张驰骋，李雷孝，杜金泽，史建平. 可编辑区块链研究综述. 计算机工程与应用. 2024(18): 32-49 . 百度学术
3.	孙林昆，蒋文保，郭阳楠，李春强. 基于密码累加器的无状态区块链性能优化. 计算机工程. 2023(02): 46-53 . 百度学术
4.	姜承扬，庞俊，贾大宇，于明鹤，信俊昌，刘晨. 结合社区发现和局部恢复码的区块链扩容研究. 计算机工程与应用. 2023(05): 297-304 . 百度学术
5.	邓文丽，方欢. 基于健康数据库的无状态区块链在医疗保健的应用. 哈尔滨商业大学学报(自然科学版). 2023(04): 408-412 . 百度学术
6.	刘孝保，孙海彬，阴艳超，姚廷强，杨林. 面向制造业产业链图状区块链模型. 计算机集成制造系统. 2023(12): 4267-4281 . 百度学术
7.	傅丽玉，陆歌皓，吴义明，罗娅玲. 区块链技术的研究及其发展综述. 计算机科学. 2022(S1): 447-461+666 . 百度学术