Projecting dependency syntax labels from English into Vietnamese in English-Vietnamese bilingual corpus

Q3 Computer Science

International Journal of Intelligent Information and Database Systems Pub Date : 2020-06-26 DOI:10.1504/ijiids.2020.10030209

Phuoc Tran, V. Duong, Dinh Dien, Bay Vo, Huu Nguyen, Long H. B. Nguyen

引用次数: 0

Abstract

In natural language processing, the corpora play an important role, particularly labelled corpora, such as labelled part-of-speech corpora, labelled component syntax corpora, and labelled dependency syntax corpora. These labelled corpora are used for corpus-based research and give higher quality results than the non-labelled. In this paper, we have conducted a Vietnamese dependency label tagger based on English-Vietnamese bilingual corpus, in which English was tagged with dependency labels. The experimental results show that our method produces a high tagging result with LAS measurement of 73.5% and UAS measurement of 81.7%.

查看原文本刊更多论文

英越双语语料库中依存句法标签从英语到越南语的投影

在自然语言处理中，语料库起着重要的作用，特别是标注语料库，如标注词性语料库、标注成分句法语料库和标注依赖句法语料库。这些标记的语料库用于基于语料库的研究，并且比未标记的语料库提供更高质量的结果。在本文中，我们基于英越双语语料库实现了一个越南语依赖标签标注器，其中英语使用依赖标签进行标注。实验结果表明，该方法具有较高的标记率，LAS测量率为73.5%，UAS测量率为81.7%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Intelligent Information and Database Systems Computer Science-Information Systems

CiteScore

2.90

自引率

0.00%

发文量

期刊介绍： Intelligent information systems and intelligent database systems are a very dynamically developing field in computer sciences. IJIIDS provides a medium for exchanging scientific research and technological achievements accomplished by the international community. It focuses on research in applications of advanced intelligent technologies for data storing and processing in a wide-ranging context. The issues addressed by IJIIDS involve solutions of real-life problems, in which it is necessary to apply intelligent technologies for achieving effective results. The emphasis of the reported work is on new and original research and technological developments rather than reports on the application of existing technology to different sets of data.