Modeling Bilingual Conversational Characteristics for Neural Chat Translation
This work addresses the problem of improving translation quality for bilingual conversational text, which is crucial for international exchanges, though it appears incremental as it builds on existing context-aware NMT methods.
The paper tackled the challenge of translating bilingual conversational text by modeling role preference, dialogue coherence, and translation consistency, resulting in a notable performance boost over strong baselines and surpassing some state-of-the-art models in BLEU and TER scores.
Neural chat translation aims to translate bilingual conversational text, which has a broad application in international exchanges and cooperation. Despite the impressive performance of sentence-level and context-aware Neural Machine Translation (NMT), there still remain challenges to translate bilingual conversational text due to its inherent characteristics such as role preference, dialogue coherence, and translation consistency. In this paper, we aim to promote the translation quality of conversational text by modeling the above properties. Specifically, we design three latent variational modules to learn the distributions of bilingual conversational characteristics. Through sampling from these learned distributions, the latent variables, tailored for role preference, dialogue coherence, and translation consistency, are incorporated into the NMT model for better translation. We evaluate our approach on the benchmark dataset BConTrasT (English-German) and a self-collected bilingual dialogue corpus, named BMELD (English-Chinese). Extensive experiments show that our approach notably boosts the performance over strong baselines by a large margin and significantly surpasses some state-of-the-art context-aware NMT models in terms of BLEU and TER. Additionally, we make the BMELD dataset publicly available for the research community.