Speculative Beam Search for Simultaneous Translation

by   Renjie Zheng, et al.

Beam search is universally used in full-sentence translation but its application to simultaneous translation remains non-trivial, where output words are committed on the fly. In particular, the recently proposed wait-k policy (Ma et al., 2019a) is a simple and effective method that (after an initial wait) commits one output word on receiving each input word, making beam search seemingly impossible. To address this challenge, we propose a speculative beam search algorithm that hallucinates several steps into the future in order to reach a more accurate decision, implicitly benefiting from a target language model. This 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 improvements over previous work.


page 1

page 2

page 3

page 4


When to Finish? Optimal Beam Search for Neural Text Generation (modulo beam size)

In neural text generation such as neural machine translation, summarizat...

What Do You Get When You Cross Beam Search with Nucleus Sampling?

We combine beam search with the probabilistic pruning technique of nucle...

Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation

Simultaneous translation is widely useful but remains challenging. Previ...

Word to Sentence Visual Semantic Similarity for Caption Generation: Lessons Learned

This paper focuses on enhancing the captions generated by image-caption ...

Finding Syntax in Human Encephalography with Beam Search

Recurrent neural network grammars (RNNGs) are generative models of (tree...

Leveraging sentence similarity in natural language generation: Improving beam search using range voting

We propose a novel method for generating natural language sentences from...

An Empirical Investigation of Beam-Aware Training in Supertagging

Structured prediction is often approached by training a locally normaliz...