Heavyweight Statistical Alignment to Guide Neural Translation

Author:

Nguyen Thien1ORCID,Nguyen Trang23ORCID

Affiliation:

1. Natural Language Processing and Knowledge Discovery Laboratory, Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, Vietnam

2. Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam

3. Vietnam National University, Ho Chi Minh City, Vietnam

Abstract

Transformer neural models with multihead attentions outperform all existing translation models. Nevertheless, some features of traditional statistical models, such as prior alignment between source and target words, prove useful in training the state-of-the-art Transformer models. It has been reported that lightweight prior alignment can effectively guide a head in the multihead cross-attention sublayer responsible for the alignment of Transformer models. In this work, we make a step further by applying heavyweight prior alignments to guide all heads. Specifically, we use the weight of 0.5 for the alignment cost added to the token cost in formulating the overall cost of training a Transformer model, where the alignment cost is defined as the deviation of the attention probability from the prior alignments. Moreover, we increase the role of prior alignment, computing the attention probability by averaging all heads of the multihead attention sublayer within the penultimate layer of Transformer model. Experimental results on an English-Vietnamese translation task show that our proposed approach helps train superior Transformer-based translation models. Our Transformer model (25.71) outperforms the baseline model (21.34) by the large 4.37 BLEU. Case studies by native speakers on some translation results validate the machine judgment. The results so far encourage the use of heavyweight prior alignments to improve Transformer-based translation models. This work contributes to the literature on the machine translation, especially, for unpopular language pairs. Since the proposal in this work is language-independent, it can be applied to different language pairs, including Slavic languages.

Publisher

Hindawi Limited

Subject

General Mathematics,General Medicine,General Neuroscience,General Computer Science

Reference46 articles.

1. The mathematics of statistical machine translation: parameter estimation;P. F. Brown;Computational Linguistics,1993

2. Statistical Machine Translation

3. Jointly Learning to Align and Translate with Transformer Models

4. A Systematic Comparison of Various Statistical Alignment Models

5. A simple, fast, and effective reparameterization of ibm model 2;C. Dyer

Cited by 2 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. Machine Translation of Electrical Terminology Constraints;Information;2023-09-20

2. Algorithm of Creating the “Uzbek-English Aligner” Program;2023 8th International Conference on Computer Science and Engineering (UBMK);2023-09-13

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