检索结果-南通市图书馆

Word-Pair Relevance Modeling with Multi-View Neural Attention Mechanism for sentence alignment

Journal of Computer Science & Technology 2020年第3期35卷 617-628页

作者： Ying Ding Jun-Hui Li Zheng-Xian Gong Guo-Dong Zhou School of Computer Science and Technology Soochow UniversitySuzhou 215006China

sentence alignment provides multi-lingual or cross-lingual natural language processing(NLP)applications with high-quality parallel sentence pairs.Normally,an aligned sentence pair contains multiple aligned words,which intuitively play different roles during sentence alignment.Inspired by this intuition,we propose to deal with the problem of sentence alignment by exploring the semantic interactionship among fine-grained word pairs within the framework of neural network.In particular,we first employ various relevance measures to capture various kinds of semantic interactions among word pairs by using a word-pair relevance network,and then model their importance by using a multi-view attention network.Experimental results on both monotonic and non-monotonic bitexts show that our proposed approach significantly improves the performance of sentence alignment.

关键词： sentence alignment neural network word-pair relevance network multi-view attention network

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Improving neural sentence alignment with word translation

引用

Frontiers of Computer Science 2021年第1期15卷 81-90页

作者： Ying DING Junhui LI Zhengxian GONG Guodong ZHOU School of Computer Science and Technology Soochow UniversitySuzhou 215006China

sentence alignment is a basic task in natural lan-guage processing which aims to extract high-quality paral-lel sentences automatically.Motivated by the observation that aligned sentence pairs contain a larger number of aligned words than unaligned ones,we treat word translation as one of the most useful external knowledge.In this paper,we show how to explicitly integrate word translation into neural sentence alignment.Specifically,this paper proposes three cross-lingual encoders to incorporate word translation:1)Mixed Encoder that learns words and their translation annotation vectors over sequences where words and their translations are mixed alterma-tively;2)Factored Encoder that views word translations as fea-tures and encodes words and their translations by concatenating their embeddings;and 3)Gated Encoder that uses gate mechanism to selectively control the amount of word translations moving forward.Experimentation on NIST MT and Opensub-titles Chinese-English datasets on both non-monotonicity and monotonicity scenarios demonstrates that all the proposed encoders significantly improve sentence alignment performance.

关键词： sentence alignment word translation mixeden coder factored encoder gated encoder

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：