Models of Translational Equivalence among Words

Author:

Melamed I. Dan1

Affiliation:

1. West Group, D1-66F, 610 Opperman Drive, Eagan, MN 55123.

Abstract

Parallel texts (bitexts) have properties that distinguish them from other kinds of parallel data. First, most words translate to only one other word. Second, bitext correspondence is typically only partial—many words in each text have no clear equivalent in the other text. This article presents methods for biasing statistical translation models to reflect these properties. Evaluation with respect to independent human judgments has confirmed that translation models biased in this fashion are significantly more accurate than a baseline knowledge-free model. This article also shows how a statistical translation model can take advantage of preexisting knowledge that might be available about particular language pairs. Even the simplest kinds of language-specific knowledge, such as the distinction between content words and function words, are shown to reliably boost translation model performance on some tasks. Statistical models that reflect knowledge about the model domain combine the best of both the rationalist and empiricist paradigms.

Publisher

MIT Press - Journals

Subject

Artificial Intelligence,Computer Science Applications,Linguistics and Language,Language and Linguistics

Cited by 57 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Building Comparable Corpora;Building and Using Comparable Corpora for Multilingual Natural Language Processing;2023

2. Basic Principles of Cross-Lingual Models;Building and Using Comparable Corpora for Multilingual Natural Language Processing;2023

3. Fast and Accurate Bilingual Lexicon Induction via Matching Optimization;Natural Language Processing and Chinese Computing;2019

4. Discourse lexicon induction for multiple languages and its use for gender profiling;Digital Scholarship in the Humanities;2018-07-24

5. Extraction of legal bilingual phrases from the Japanese Official Gazette, English Edition;Journal of Information and Telecommunication;2017-10-20

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3