Learning Coupled Policies for Simultaneous Machine Translation

02/11/2020
by   Philip Arthur, et al.
15

In simultaneous machine translation, the system needs to incrementally generate the output translation before the input sentence ends. This is a coupled decision process consisting of a programmer and interpreter. The programmer's policy decides about when to WRITE the next output or READ the next input, and the interpreter's policy decides what word to write. We present an imitation learning (IL) approach to efficiently learn effective coupled programmer-interpreter policies. To enable IL, we present an algorithmic oracle to produce oracle READ/WRITE actions for training bilingual sentence-pairs using the notion of word alignments. We attribute the effectiveness of the learned coupled policies to (i) scheduled sampling addressing the coupled exposure bias, and (ii) quality of oracle actions capturing enough information from the partial input before writing the output. Experiments show our method outperforms strong baselines in terms of translation quality and delay, when translating from German/Arabic/Czech/Bulgarian/Romanian to English.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/21/2023

LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation

Simultaneous machine translation, which aims at a real-time translation,...
research
03/17/2022

Modeling Dual Read/Write Paths for Simultaneous Machine Translation

Simultaneous machine translation (SiMT) outputs translation while readin...
research
09/04/2019

Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation

Simultaneous translation is widely useful but remains challenging. Previ...
research
09/09/2021

Fixing exposure bias with imitation learning needs powerful oracles

We apply imitation learning (IL) to tackle the NMT exposure bias problem...
research
04/27/2022

Data-Driven Adaptive Simultaneous Machine Translation

In simultaneous translation (SimulMT), the most widely used strategy is ...
research
06/04/2019

Simultaneous Translation with Flexible Policy via Restricted Imitation Learning

Simultaneous translation is widely useful but remains one of the most di...
research
07/18/2022

MAD for Robust Reinforcement Learning in Machine Translation

We introduce a new distributed policy gradient algorithm and show that i...

Please sign up or login with your details

Forgot password? Click here to reset