Knowledge Commons of Institute of Automation,CAS
Conducting Natural Language Inference with Word-Pair-Dependency and Local Context | |
Du, Qianlong1,2; Zong, Chengqing1,2,3; Su, Keh-Yih4 | |
发表期刊 | ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING |
ISSN | 2375-4699 |
2020-07-01 | |
卷号 | 19期号:3页码:23 |
产权排序 | 1 |
文章类型 | 期刊论文 |
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). |
关键词 | Natural language inference textual entailment syntactic relation local context relation triplet word-pair dependency |
DOI | 10.1145/3377704 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Program of China[2016QY02D0303] ; National Key Research and Development Program of China[2016QY02D0303] |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000582616600014 |
出版者 | ASSOC COMPUTING MACHINERY |
七大方向——子方向分类 | 自然语言处理 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/41810 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
通讯作者 | Zong, Chengqing |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology 4.Institute of Information Science, Academia Sinica |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
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. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Conducting Natural L(1838KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 |
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。
修改评论