Speculative Beam Search for Simultaneous Translation

Beam search is universally used in (full-sentence) machine translation but its application to simultaneous translation remains highly non-trivial, where output words are committed on the fly. In particular, the recently proposed wait-k policy (Ma et al., 2018) is a simple and effective method that (after an initial wait) commits one output word on receiving each input word, making beam search seemingly inapplicable. To address this challenge, we propose a new speculative beam search algorithm that hallucinates several steps into the future in order to reach a more accurate decision by implicitly benefiting from a target language model. This idea makes beam search applicable for the first time to the generation of a single word in each step. Experiments over diverse language pairs show large improvement compared to previous work.

[1]  Renjie Zheng,et al.  Learning to Stop in Structured Prediction for Neural Machine Translation , 2019, NAACL-HLT.

[2]  Wei Li,et al.  Monotonic Infinite Lookback Attention for Simultaneous Machine Translation , 2019, ACL.

[3]  Tomoki Toda,et al.  Syntax-based Simultaneous Translation through Prediction of Unseen Syntactic Constituents , 2015, ACL.

[4]  Marc'Aurelio Ranzato,et al.  Sequence Level Training with Recurrent Neural Networks , 2015, ICLR.

[5]  Haifeng Wang,et al.  STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework , 2018, ACL.

[6]  Samy Bengio,et al.  An Online Sequence-to-Sequence Model Using Partial Conditioning , 2015, NIPS.

[7]  Samy Bengio,et al.  Show and tell: A neural image caption generator , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Jordan L. Boyd-Graber,et al.  Don't Until the Final Verb Wait: Reinforcement Learning for Simultaneous Machine Translation , 2014, EMNLP.

[9]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[10]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[11]  Rico Sennrich,et al.  Neural Machine Translation of Rare Words with Subword Units , 2015, ACL.

[12]  Graham Neubig,et al.  Learning to Translate in Real-time with Neural Machine Translation , 2016, EACL.

[13]  Alexander M. Rush,et al.  OpenNMT: Open-Source Toolkit for Neural Machine Translation , 2017, ACL.

[14]  David Chiang,et al.  Correcting Length Bias in Neural Machine Translation , 2018, WMT.

[15]  Renjie Zheng,et al.  Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation , 2019, EMNLP.

[16]  Nadir Durrani,et al.  Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation , 2018, NAACL.

[17]  Tara N. Sainath,et al.  State-of-the-Art Speech Recognition with Sequence-to-Sequence Models , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[18]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[19]  Renjie Zheng,et al.  Simultaneous Translation with Flexible Policy via Restricted Imitation Learning , 2019, ACL.

[20]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[21]  Srinivas Bangalore,et al.  Real-time Incremental Speech-to-Speech Translation of Dialogs , 2012, NAACL.

[22]  Jason Weston,et al.  A Neural Attention Model for Abstractive Sentence Summarization , 2015, EMNLP.

[23]  Mingbo Ma,et al.  When to Finish? Optimal Beam Search for Neural Text Generation (modulo beam size) , 2017, EMNLP.