paper-with-me

홈 › Papers

Modeling Future for Neural Machine Translation by Fusing Target Information

2021-09-17 · ACL ARR September 2021 9 · Anonymous

Sequence-to-sequence Neural Machine Translation (NMT) models have achieved excellent performance. However, the NMT decoder only makes predictions based on the source and the target historical context, ignores the target future information completely, leading to a problem that NMT does not consider potential future information when making decisions. To alleviate this problem, we propose a simple and effective {\bf Fu}ture-fused {\bf NMT} model called \textsc{FuNMT}, which introduces a reverse decoder to explicitly model the target future information, then adopts an agreement mechanism to enable the forward decoder to learn this future information. Empirical studies on multiple benchmarks show that our proposed model significantly improves translation quality.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Dual Past and Future for Neural Machine Translation

2020-07-15 · Jianhao Yan, Fandong Meng, Jie zhou

Though remarkable successes have been achieved by Neural Machine Translation (NMT) in recent years, it still suffers from the inadequate-translation problem. Previous studies show that explicitly modeling the Past and Fu…

Machine TranslationNMTSentenceTranslation

Modeling Future Cost for Neural Machine Translation

2020-02-28 · Chaoqun Duan, Kehai Chen, Rui Wang, Masao Utiyama 외

Existing neural machine translation (NMT) systems utilize sequence-to-sequence neural networks to generate target translation word by word, and then make the generated word at each time-step and the counterpart in the re…

Machine TranslationNMTTranslation

Infusing Future Information into Monotonic Attention Through Language Models

2021-09-07 · Mohd Abbas Zaidi, Sathish Indurthi, Beomseok Lee, Nikhil Kumar Lakumarapu 외

Simultaneous neural machine translation(SNMT) models start emitting the target sequence before they have processed the source sequence. The recent adaptive policies for SNMT use monotonic attention to perform read/write …

Language ModelingLanguage ModellingMachine TranslationSpeech-to-Text+2

Automatic Evaluation and Analysis of Idioms in Neural Machine Translation

2022-10-10 · Christos Baziotis, Prashant Mathur, Eva Hasler

A major open problem in neural machine translation (NMT) is the translation of idiomatic expressions, such as "under the weather". The meaning of these expressions is not composed by the meaning of their constituent word…

Machine TranslationNMTTranslation

Modeling Fluency and Faithfulness for Diverse Neural Machine Translation

2019-11-30 · Yang Feng, Wanying Xie, Shuhao Gu, Chenze Shao 외

Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach …

Machine TranslationPredictionTranslation