paper-with-me

홈 › Papers

Learning to Stop in Structured Prediction for Neural Machine Translation

2019-04-01 · NAACL 2019 6 · Mingbo Ma, Renjie Zheng, Liang Huang

Beam search optimization resolves many issues in neural machine translation. However, this method lacks principled stopping criteria and does not learn how to stop during training, and the model naturally prefers the longer hypotheses during the testing time in practice since they use the raw score instead of the probability-based score. We propose a novel ranking method which enables an optimal beam search stopping criteria. We further introduce a structured prediction loss function which penalizes suboptimal finished candidates produced by beam search during training. Experiments of neural machine translation on both synthetic data and real languages (German-to-English and Chinese-to-English) demonstrate our proposed methods lead to better length and BLEU score.

📄 PDF Abstract BibTeX arXiv:1904.01032

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationStructured PredictionTranslation

Similar Papers 제목 키워드 기반

Bandit Structured Prediction for Learning from Partial Feedback in Statistical Machine Translation

2016-01-18 · Artem Sokolov, Stefan Riezler, Tanguy Urvoy

We present an approach to structured prediction from bandit feedback, called Bandit Structured Prediction, where only the value of a task loss function at a single predicted point, instead of a correct structure, is obse…

Machine TranslationRerankingStructured PredictionTranslation

Future-Prediction-Based Model for Neural Machine Translation

2018-09-02 · Bingzhen Wei, Junyang Lin

We propose a novel model for Neural Machine Translation (NMT). Different from the conventional method, our model can predict the future text length and words at each decoding time step so that the generation can be helpe…

Future predictionMachine TranslationNMTPrediction+1

A General Framework for Adaptation of Neural Machine Translation to Simultaneous Translation

2019-11-08 · Asian Chapter of the Association for Computational Linguistics 2020 · Yun Chen, Liangyou Li, Xin Jiang, Xiao Chen 외

Despite the success of neural machine translation (NMT), simultaneous neural machine translation (SNMT), the task of translating in real time before a full sentence has been observed, remains challenging due to the synta…

Machine TranslationNMTSentenceTranslation

Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation

2018-08-28 · EMNLP 2018 10 · Yilin Yang, Liang Huang, Mingbo Ma

Beam search is widely used in neural machine translation, and usually improves translation quality compared to greedy search. It has been widely observed that, however, beam sizes larger than 5 hurt translation quality. …

Machine TranslationTranslation

A Coactive Learning View of Online Structured Prediction in Statistical Machine Translation

2015-07-01 · CONLL 2015 7 · Artem Sokolov, Stefan Riezler, Shay B. Cohen
Machine TranslationStructured PredictionTranslation