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

TL;DR

This paper introduces a Wait-info Policy for simultaneous machine translation that balances source and target information at the information level, leading to improved translation performance.

Contribution

It proposes a novel info-based balancing method that considers information content per token, unlike previous token-level approaches.

Findings

Outperforms strong baseline methods.

Achieves better balance between source and target information.

Demonstrates effectiveness of info-based decision making.

Abstract

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.