中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Conducting Natural Language Inference with Word-Pair-Dependency and Local Context

文献类型:期刊论文

作者Du, Qianlong1,4; Zong, Chengqing1,2,4; Su, Keh-Yih3
刊名ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING
出版日期2020-07-01
卷号19期号:3页码:23
关键词Natural language inference textual entailment syntactic relation local context relation triplet word-pair dependency
ISSN号2375-4699
DOI10.1145/3377704
产权排序1
文献子类期刊论文
英文摘要

This article proposes to conduct natural language inference with novel Enhanced-Relation-Head-Dependent triplets (RHD triplets), which are constructed via enhancing each word in the RHD triplet with its associated local context. Most previous approaches based on deep neural network (DNN) for this task either perform token alignment without considering syntactic dependency among words, or directly use tree-LSTM to generate passage representation with irrelevant information. To improve token alignment and inference judgment with word-pair-dependency, the RHD triplet structure is first proposed. To avoid incorporating irrelevant information, this proposed approach performs comparison directly on each triplet-pair of the given passage-pair (instead of comparing each triplet in a passage with the content merged from the whole opposite passage). Furthermore, to take local context into consideration while conducting token alignment and inference judgment, we also enhance the words of the triplets with their associated local context to improve the performance. Experimental results show that the proposed approach is better than most previous approaches that adopt tree structures, and its performance is comparable to other state-of-the-art approaches (however, our approach is more human comprehensible).

资助项目National Key Research and Development Program of China[2016QY02D0303] ; National Key Research and Development Program of China
WOS研究方向Computer Science
项目编号2016QY02D0303
语种英语
WOS记录号WOS:000582616600014
出版者ASSOC COMPUTING MACHINERY
资助机构National Key Research and Development Program of China
源URL[http://ir.ia.ac.cn/handle/173211/41809]  
专题模式识别国家重点实验室_自然语言处理
通讯作者Zong, Chengqing
作者单位1.University of Chinese Academy of Sciences
2.CAS Center for Excellence in Brain Science and Intelligence Technology
3.Institute of Information Science, Academia Sinica
4.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Du, Qianlong,Zong, Chengqing,Su, Keh-Yih. Conducting Natural Language Inference with Word-Pair-Dependency and Local Context[J]. ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING,2020,19(3):23.
APA Du, Qianlong,Zong, Chengqing,&Su, Keh-Yih.(2020).Conducting Natural Language Inference with Word-Pair-Dependency and Local Context.ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING,19(3),23.
MLA Du, Qianlong,et al."Conducting Natural Language Inference with Word-Pair-Dependency and Local Context".ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING 19.3(2020):23.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。