Infusing Future Information into Monotonic Attention Through Language Models

Sathish Reddy Indurthi, Mohd Abbas Zaidi, Beomseok Lee, Nikhil Kumar Lakumarapu, Sangha Kim

Keywords: Simultaneous Translation, Monotonic Attention, Speech Translation

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. 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-CEnglish-German and English-French speech-to-text translation tasks to show the effectiveness of the proposed framework. It improves the quality-latency trade-off over the state-of-the-art monotonic multihead attention.

One-sentence Summary: Helping the monotonic attention to take read/write decisions in simultaneous translation using plausible future information