Infusing Future Information into Monotonic Attention Through Language Models

TL;DR

This paper introduces a framework that enhances monotonic attention in simultaneous neural machine translation by integrating an external language model, leading to improved translation quality and latency trade-offs.

Contribution

It proposes a novel method to incorporate future information via an external language model into monotonic attention for SNMT, inspired by human translation strategies.

Findings

Improved quality-latency trade-off over state-of-the-art methods

Effective in English-German and English-French speech translation tasks

Demonstrates the benefit of future information infusion in monotonic attention

Abstract

Simultaneous neural machine translation(SNMT) models start emitting the target sequence before they have processed the source sequence. The recent adaptive policies for SNMT use monotonic attention to perform read/write decisions based on the partial source and target sequences. The lack of sufficient information might cause the monotonic attention to take poor read/write decisions, which in turn negatively affects the performance of the SNMT model. On the other hand, human translators make better read/write decisions since they can anticipate the immediate future words using linguistic information and domain knowledge.Motivated by human translators, in this work, we propose a framework to aid monotonic attention with an external language model to improve its decisions.We conduct experiments on the MuST-C English-German and English-French speech-to-text translation tasks to show the effectiveness of the proposed framework.The proposed SNMT method improves the quality-latency trade-off over the state-of-the-art monotonic multihead attention.