DuTongChuan: Context-aware Translation Model for Simultaneous Interpreting

TL;DR

DuTongChuan is a context-aware simultaneous interpreting model that balances translation quality and latency by dynamically detecting information units and applying effective decoding strategies, achieving high coherence and low delay.

Contribution

The paper introduces a novel context-aware translation model for simultaneous interpreting that dynamically detects information units and employs simple decoding strategies to improve translation quality and reduce latency.

Findings

Achieves 85.71% translation quality for Chinese-English

Reduces latency to less than 3 seconds in most cases

Demonstrates effective discourse coherence in translations

Abstract

In this paper, we present DuTongChuan, a novel context-aware translation model for simultaneous interpreting. This model allows to constantly read streaming text from the Automatic Speech Recognition (ASR) model and simultaneously determine the boundaries of Information Units (IUs) one after another. The detected IU is then translated into a fluent translation with two simple yet effective decoding strategies: partial decoding and context-aware decoding. In practice, by controlling the granularity of IUs and the size of the context, we can get a good trade-off between latency and translation quality easily. Elaborate evaluation from human translators reveals that our system achieves promising translation quality (85.71% for Chinese-English, and 86.36% for English-Chinese), specially in the sense of surprisingly good discourse coherence. According to an End-to-End (speech-to-speech simultaneous interpreting) evaluation, this model presents impressive performance in reducing latency (to less than 3 seconds at most times). Furthermore, we successfully deploy this model in a variety of Baidu's products which have hundreds of millions of users, and we release it as a service in our AI platform.