Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation

10/20/2022
by   Shaolei Zhang, et al.
0

Simultaneous machine translation (SiMT) outputs the translation while receiving the source inputs, and hence needs to balance the received source information and translated target information to make a reasonable decision between waiting for inputs or outputting translation. Previous methods always balance source and target information at the token level, either directly waiting for a fixed number of tokens or adjusting the waiting based on the current token. In this paper, we propose a Wait-info Policy to balance source and target at the information level. We first quantify the amount of information contained in each token, named info. Then during simultaneous translation, the decision of waiting or outputting is made based on the comparison results between the total info of previous target outputs and received source inputs. Experiments show that our method outperforms strong baselines under and achieves better balance via the proposed info.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/22/2022

Information-Transport-based Policy for Simultaneous Translation

Simultaneous translation (ST) outputs translation while receiving the so...
research
09/12/2023

Glancing Future for Simultaneous Machine Translation

Simultaneous machine translation (SiMT) outputs translation while readin...
research
11/02/2020

Focus on the present: a regularization method for the ASR source-target attention layer

This paper introduces a novel method to diagnose the source-target atten...
research
03/17/2022

Gaussian Multi-head Attention for Simultaneous Machine Translation

Simultaneous machine translation (SiMT) outputs translation while receiv...
research
12/22/2017

Source-side Prediction for Neural Headline Generation

The encoder-decoder model is widely used in natural language generation ...
research
03/01/2023

Hidden Markov Transformer for Simultaneous Machine Translation

Simultaneous machine translation (SiMT) outputs the target sequence whil...
research
05/25/2018

Recursive Neural Network Based Preordering for English-to-Japanese Machine Translation

The word order between source and target languages significantly influen...

Please sign up or login with your details

Forgot password? Click here to reset