Contextual Neural Model for Translating Bilingual Multi-Speaker Conversations

TL;DR

This paper introduces a neural translation model tailored for bilingual multi-speaker conversations, emphasizing the importance of conversation history for improved translation quality, validated through new datasets and experiments across multiple language pairs.

Contribution

The paper proposes a novel neural architecture for translating bilingual multi-speaker conversations and introduces new datasets for evaluating this task.

Findings

Leveraging conversation history improves translation quality.

Models outperform baselines in BLEU and manual evaluations.

New datasets enable evaluation of multi-speaker conversation translation.

Abstract

Recent works in neural machine translation have begun to explore document translation. However, translating online multi-speaker conversations is still an open problem. In this work, we propose the task of translating Bilingual Multi-Speaker Conversations, and explore neural architectures which exploit both source and target-side conversation histories for this task. To initiate an evaluation for this task, we introduce datasets extracted from Europarl v7 and OpenSubtitles2016. Our experiments on four language-pairs confirm the significance of leveraging conversation history, both in terms of BLEU and manual evaluation.