Efficient Wait-k Models for Simultaneous Machine Translation - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Efficient Wait-k Models for Simultaneous Machine Translation

Abstract

Simultaneous machine translation consists in starting output generation before the entire input sequence is available. Wait-k decoders offer a simple but efficient approach for this problem. They first read k source tokens, after which they alternate between producing a target token and reading another source token. We investigate the behavior of wait-k decoding in low resource settings for spoken corpora using IWSLT datasets. We improve training of these models using unidirectional encoders, and training across multiple values of k. Experiments with Transformer and 2D-convolutional architectures show that our wait-k models generalize well across a wide range of latency levels. We also show that the 2D-convolution architecture is competitive with Transformers for simultaneous translation of spoken language.
Fichier principal
Vignette du fichier
Waitk_decoding__InterSpeech_2020_.pdf (385.16 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02962195 , version 1 (09-10-2020)

Identifiers

Cite

Maha Elbayad, Laurent Besacier, Jakob Verbeek. Efficient Wait-k Models for Simultaneous Machine Translation. Interspeech 2020 - Conference of the International Speech Communication Association, Oct 2020, Shangai (Virtual Conf), China. pp.1461--1465, ⟨10.21437/Interspeech.2020-1241⟩. ⟨hal-02962195⟩
227 View
196 Download

Altmetric

Share

Gmail Facebook X LinkedIn More