Minimum Risk Training for Neural Machine Translation

Shen, Suhung; Cheng, Yong; He, Zuyuan; He, Wei; Wu, Hua; Sun, Maosong; Liu, Yang

doi:10.18653/v1/p16-1159

Cited by 345 publications

(358 citation statements)

References 19 publications

Supporting

Mentioning

356

Contrasting

Order By: Relevance

“…For online translation services, decoding speed is a crucial factor to achieve a better user experience. Several recently proposed training methods (Shen et al, 2015;Wiseman and Rush, 2016) aim to solve the exposure bias problem, but require decoding the whole training set multiple times, which is extremely time-consuming for millions of sentences.…”

Section: Introductionmentioning

confidence: 99%

Speeding Up Neural Machine Translation Decoding by Shrinking Run-time Vocabulary

Shi¹,

Knight²

2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 2: Short Papers)

View full text Add to dashboard Cite

We speed up Neural Machine Translation (NMT) decoding by shrinking run-time target vocabulary. We experiment with two shrinking approaches: Locality Sensitive Hashing (LSH) and word alignments. Using the latter method, we get a 2x overall speed-up over a highly-optimized GPU implementation, without hurting BLEU. On certain low-resource language pairs, the same methods improve BLEU by 0.5 points. We also report a negative result for LSH on GPUs, due to relatively large overhead, though it was successful on CPUs. Compared with Locality Sensitive Hashing (LSH), decoding with word alignments is GPU-friendly, orthogonal to existing speedup methods and more robust across language pairs.

show abstract

Section: Introductionmentioning

confidence: 99%

Speeding Up Neural Machine Translation Decoding by Shrinking Run-time Vocabulary

Shi¹,

Knight²

2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 2: Short Papers)

View full text Add to dashboard Cite

show abstract

“…A terminal reward is received when the policy finishes generating sequence. [Shen et al, 2016] propose the minimum risk training to minimize the expected loss on the training data, which is in the same spirit as RL formulation to directly optimize the evaluation metric. argues that immediate reward is good for faster convergence, and makes reward signal less sparse.…”

Section: Related Workmentioning

confidence: 99%

Sequence Prediction with Unlabeled Data by Reward Function Learning

Qin

et al. 2017

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Reinforcement learning (RL), which has been successfully applied to sequence prediction, introduces reward as sequence-level supervision signal to evaluate the quality of a generated sequence. Existing RL approaches use the ground-truth sequence to define reward, which limits the application of RL techniques to labeled data. Since labeled data is usually scarce and/or costly to collect, it is desirable to leverage large-scale unlabeled data. In this paper, we extend existing RL methods for sequence prediction to exploit unlabeled data. We propose to learn the reward function from labeled data and use the predicted reward as pseudo reward for unlabeled data so that we can learn from unlabeled data using the pseudo reward. To get good pseudo reward on unlabeled data, we propose a RNN-based reward network with attention mechanism, trained with purposely biased data distribution. Experiments show that the pseudo reward can provide good supervision and guide the learning process on unlabeled data. We observe significant improvements on both neural machine translation and text summarization.

show abstract

“…Most of existing work in neural machine translation focus on handling rare words [12,20,15], integrating SMT strategies [6,28,24,21], designing the better framework [23,14,16] and addressing the low resource scenario [2,27,19].…”

Section: Related Workmentioning

confidence: 99%

Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT

Wang

Zhang

et al. 2017

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract. Neural machine translation (NMT), a new approach to machine translation, has been proved to outperform conventional statistical machine translation (SMT) across a variety of language pairs. Translation is an open-vocabulary problem, but most existing NMT systems operate with a fixed vocabulary, which causes the incapability of translating rare words. This problem can be alleviated by using different translation granularities, such as character, subword and hybrid word-character. Translation involving Chinese is one of the most difficult tasks in machine translation, however, to the best of our knowledge, there has not been any other work exploring which translation granularity is most suitable for Chinese in NMT. In this paper, we conduct an extensive comparison using Chinese-English NMT as a case study. Furthermore, we discuss the advantages and disadvantages of various translation granularities in detail. Our experiments show that subword model performs best for Chinese-to-English translation with the vocabulary which is not so big while hybrid word-character model is most suitable for Englishto-Chinese translation. Moreover, experiments of different granularities show that Hybrid BPE method can achieve best result on Chinese-toEnglish translation task.

show abstract

Minimum Risk Training for Neural Machine Translation

Cited by 345 publications

References 19 publications

Speeding Up Neural Machine Translation Decoding by Shrinking Run-time Vocabulary

Speeding Up Neural Machine Translation Decoding by Shrinking Run-time Vocabulary

Sequence Prediction with Unlabeled Data by Reward Function Learning

Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT

Contact Info

Product

Resources

About