Who Is Speaking to Whom? Learning to Identify Utterance Addressee in Multi-Party Conversations

Previous research on dialogue systems generally focuses on the conversation between two participants, yet multi-party conversations which involve more than two participants within one session bring up a more complicated but realistic scenario. In real multiparty conversations, we can observe who is speaking, but the addressee information is not always explicit. In this paper, we aim to tackle the challenge of identifying all the missing addressees in a conversation session. To this end, we introduce a novel who-to-whom (W2W) model which models users and utterances in the session jointly in an interactive way. We conduct experiments on the benchmark Ubuntu Multi-Party Conversation Corpus and the experimental results demonstrate that our model outperforms baselines with consistent improvements.