paper-with-me

홈 › Papers

Effective Use of Target-side Context for Neural Machine Translation

2020-12-01 · COLING 2020 8 · Hideya Mino, Hitoshi Ito, Isao Goto, Ichiro Yamada, Takenobu Tokunaga

In this paper, we deal with two problems in Japanese-English machine translation of news articles. The first problem is the quality of parallel corpora. Neural machine translation (NMT) systems suffer degraded performance when trained with noisy data. Because there is no clean Japanese-English parallel data for news articles, we build a novel parallel news corpus consisting of Japanese news articles translated into English in a content-equivalent manner. This is the first content-equivalent Japanese-English news corpus translated specifically for training NMT systems. The second problem involves the domain-adaptation technique. NMT systems suffer degraded performance when trained with mixed data having different features, such as noisy data and clean data. Though the existing methods try to overcome this problem by using tags for distinguishing the differences between corpora, it is not sufficient. We thus extend a domain-adaptation method using multi-tags to train an NMT model effectively with the clean corpus and existing parallel news corpora with some types of noise. Experimental results show that our corpus increases the translation quality, and that our domain-adaptation method is more effective for learning with the multiple types of corpora than existing domain-adaptation methods are.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ArticlesDomain AdaptationMachine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Improving Context-aware Neural Machine Translation with Target-side Context

2019-09-02 · Hayahide Yamagishi, Mamoru Komachi

In recent years, several studies on neural machine translation (NMT) have attempted to use document-level context by using a multi-encoder and two attention mechanisms to read the current and previous sentences to incorp…

DecoderMachine TranslationNMTSentence+1

Synchronous Refinement for Neural Machine Translation

2022-05-01 · Findings (ACL) 2022 5 · Kehai Chen, Masao Utiyama, Eiichiro Sumita, Rui Wang 외

Machine translation typically adopts an encoder-to-decoder framework, in which the decoder generates the target sentence word-by-word in an auto-regressive manner. However, the auto-regressive decoder faces a deep-rooted…

DecoderMachine TranslationSentenceTranslation

Document Context Neural Machine Translation with Memory Networks

2017-11-10 · ACL 2018 7 · Sameen Maruf, Gholamreza Haffari

We present a document-level neural machine translation model which takes both source and target document context into account using memory networks. We model the problem as a structured prediction problem with interdepen…

Machine TranslationStructured PredictionTranslation

Deconvolution-Based Global Decoding for Neural Machine Translation

2018-06-10 · COLING 2018 8 · Junyang Lin, Xu sun, Xuancheng Ren, Shuming Ma 외

A great proportion of sequence-to-sequence (Seq2Seq) models for Neural Machine Translation (NMT) adopt Recurrent Neural Network (RNN) to generate translation word by word following a sequential order. As the studies of l…

Machine TranslationNMTTranslation

Target-Side Context for Discriminative Models in Statistical Machine Translation

2016-07-05 · ACL 2016 8 · Aleš Tamchyna, Alexander Fraser, Ondřej Bojar, Marcin Junczys-Dowmunt

Discriminative translation models utilizing source context have been shown to help statistical machine translation performance. We propose a novel extension of this work using target context information. Surprisingly, we…

Machine TranslationTranslation