Contextual Neural Model for Translating Bilingual Multi-Speaker Conversations
This addresses the challenge of translating online multi-speaker conversations, which is an incremental advancement over existing document translation methods.
The paper tackles the problem of translating bilingual multi-speaker conversations by proposing neural architectures that use source and target-side conversation histories, and shows that leveraging this history improves translation performance in terms of BLEU scores and manual evaluation across four language-pairs.
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.