paper-with-me

홈 › Papers

Minimum Risk Training for Neural Machine Translation

2015-12-08 · ACL 2016 8 · Shiqi Shen, Yong Cheng, Zhongjun He, wei he, Hua Wu, Maosong Sun, Yang Liu

We propose minimum risk training for end-to-end neural machine translation. Unlike conventional maximum likelihood estimation, minimum risk training is capable of optimizing model parameters directly with respect to arbitrary evaluation metrics, which are not necessarily differentiable. Experiments show that our approach achieves significant improvements over maximum likelihood estimation on a state-of-the-art neural machine translation system across various languages pairs. Transparent to architectures, our approach can be applied to more neural networks and potentially benefit more NLP tasks.

📄 PDF Abstract BibTeX arXiv:1512.02433

Code (1)

kh-kim/simple-nmt pytorch

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Lexicons and Minimum Risk Training for Neural Machine Translation: NAIST-CMU at WAT2016

2016-10-20 · WS 2016 12 · Graham Neubig

This year, the Nara Institute of Science and Technology (NAIST)/Carnegie Mellon University (CMU) submission to the Japanese-English translation track of the 2016 Workshop on Asian Translation was based on attentional neu…

Machine TranslationNMTTranslation

THUMT: An Open Source Toolkit for Neural Machine Translation

2017-06-20 · Jiacheng Zhang, Yanzhuo Ding, Shiqi Shen, Yong Cheng 외

This paper introduces THUMT, an open-source toolkit for neural machine translation (NMT) developed by the Natural Language Processing Group at Tsinghua University. THUMT implements the standard attention-based encoder-de…

DecoderMachine TranslationNMTTranslation

Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation

2021-05-18 · ACL 2021 5 · Mathias Müller, Rico Sennrich

Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words, and shows poor robustness to copy noise in training data or domain shift. Re…

Machine TranslationNMTTranslation

Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET

2022-02-10 · Chantal Amrhein, Rico Sennrich

Neural metrics have achieved impressive correlation with human judgements in the evaluation of machine translation systems, but before we can safely optimise towards such metrics, we should be aware of (and ideally elimi…

de-enMachine TranslationTranslation

BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training

2023-07-06 · Yiming Yan, Tao Wang, Chengqi Zhao, ShuJian Huang 외

Automatic metrics play a crucial role in machine translation. Despite the widespread use of n-gram-based metrics, there has been a recent surge in the development of pre-trained model-based metrics that focus on measurin…

Machine TranslationSentenceTranslation