Neural Simultaneous Speech Translation Using Alignment-Based Chunking

Patrick Wilken, Tamer Alkhouli, Evgeny Matusov, Pavel Golik


Abstract
In simultaneous machine translation, the objective is to determine when to produce a partial translation given a continuous stream of source words, with a trade-off between latency and quality. We propose a neural machine translation (NMT) model that makes dynamic decisions when to continue feeding on input or generate output words. The model is composed of two main components: one to dynamically decide on ending a source chunk, and another that translates the consumed chunk. We train the components jointly and in a manner consistent with the inference conditions. To generate chunked training data, we propose a method that utilizes word alignment while also preserving enough context. We compare models with bidirectional and unidirectional encoders of different depths, both on real speech and text input. Our results on the IWSLT 2020 English-to-German task outperform a wait-k baseline by 2.6 to 3.7% BLEU absolute.
Anthology ID:
2020.iwslt-1.29
Volume:
Proceedings of the 17th International Conference on Spoken Language Translation
Month:
July
Year:
2020
Address:
Online
Editors:
Marcello Federico, Alex Waibel, Kevin Knight, Satoshi Nakamura, Hermann Ney, Jan Niehues, Sebastian Stüker, Dekai Wu, Joseph Mariani, Francois Yvon
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
237–246
Language:
URL:
https://aclanthology.org/2020.iwslt-1.29
DOI:
10.18653/v1/2020.iwslt-1.29
Bibkey:
Cite (ACL):
Patrick Wilken, Tamer Alkhouli, Evgeny Matusov, and Pavel Golik. 2020. Neural Simultaneous Speech Translation Using Alignment-Based Chunking. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 237–246, Online. Association for Computational Linguistics.
Cite (Informal):
Neural Simultaneous Speech Translation Using Alignment-Based Chunking (Wilken et al., IWSLT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.iwslt-1.29.pdf
Video:
 http://slideslive.com/38929608
Data
MuST-C