-
When to Finish? Optimal Beam Search for Neural Text Generation (modulo beam size)
In neural text generation such as neural machine translation, summarizat...
read it
-
Leveraging sentence similarity in natural language generation: Improving beam search using range voting
We propose a novel method for generating natural language sentences from...
read it
-
Finding Syntax in Human Encephalography with Beam Search
Recurrent neural network grammars (RNNGs) are generative models of (tree...
read it
-
Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation
Simultaneous translation is widely useful but remains challenging. Previ...
read it
-
An Empirical Investigation of Beam-Aware Training in Supertagging
Structured prediction is often approached by training a locally normaliz...
read it
-
Learning Optimal Tree Models Under Beam Search
Retrieving relevant targets from an extremely large target set under com...
read it
-
Lost in Interpretation: Predicting Untranslated Terminology in Simultaneous Interpretation
Simultaneous interpretation, the translation of speech from one language...
read it
Speculative Beam Search for Simultaneous Translation
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.
READ FULL TEXT
Comments
There are no comments yet.