paper-with-me

Papers

Modeling Coverage for Non-Autoregressive Neural Machine Translation

2021-04-24 · Yong Shan, Yang Feng, Chenze Shao

Non-Autoregressive Neural Machine Translation (NAT) has achieved significant inference speedup by generating all tokens simultaneously. Despite its high efficiency, NAT usually suffers from two kinds of translation errors: over-translation (e.g. repeated tokens) and under-translation (e.g. missing translations), which eventually limits the translation quality. In this paper, we argue that these issues of NAT can be addressed through coverage modeling, which has been proved to be useful in autoregressive decoding. We propose a novel Coverage-NAT to model the coverage information directly by a token-level coverage iterative refinement mechanism and a sentence-level coverage agreement, which can remind the model if a source token has been translated or not and improve the semantics consistency between the translation and the source, respectively. Experimental results on WMT14 En-De and WMT16 En-Ro translation tasks show that our method can alleviate those errors and achieve strong improvements over the baseline system.

📄 PDF Abstract BibTeX arXiv:2104.11897

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationSentenceTranslation

Similar Papers 제목 키워드 기반

Shared Latent Space by Both Languages in Non-Autoregressive Neural Machine Translation

2023-05-02 · DongNyeong Heo, Heeyoul Choi

Non-autoregressive neural machine translation (NAT) offers substantial translation speed up compared to autoregressive neural machine translation (AT) at the cost of translation quality. Latent variable modeling has emer…

Machine TranslationTranslation

Modeling Coverage for Neural Machine Translation

2016-01-19 · ACL 2016 8 · Zhaopeng Tu, Zhengdong Lu, Yang Liu, Xiaohua Liu 외

Attention mechanism has enhanced state-of-the-art Neural Machine Translation (NMT) by jointly learning to align and translate. It tends to ignore past alignment information, however, which often leads to over-translation…

Machine TranslationNMTTranslation

Non-Autoregressive Translation by Learning Target Categorical Codes

2021-03-21 · NAACL 2021 4 · Yu Bao, ShuJian Huang, Tong Xiao, Dongqi Wang 외

Non-autoregressive Transformer is a promising text generation model. However, current non-autoregressive models still fall behind their autoregressive counterparts in translation quality. We attribute this accuracy gap t…

AttributeDecoderMachine TranslationText Generation+1

The RoyalFlush System for the WMT 2022 Efficiency Task

2022-12-03 · Bo Qin, Aixin Jia, Qiang Wang, Jianning Lu 외

This paper describes the submission of the RoyalFlush neural machine translation system for the WMT 2022 translation efficiency task. Unlike the commonly used autoregressive translation system, we adopted a two-stage tra…

DecoderGPUKnowledge DistillationMachine Translation+1

Aligned Cross Entropy for Non-Autoregressive Machine Translation

2020-04-03 · ICML 2020 1 · Marjan Ghazvininejad, Vladimir Karpukhin, Luke Zettlemoyer, Omer Levy

Non-autoregressive machine translation models significantly speed up decoding by allowing for parallel prediction of the entire target sequence. However, modeling word order is more challenging due to the lack of autoreg…

Machine TranslationTranslation