Structural Characterization for Dialogue Disentanglement

Anonymous

Abstract: Tangled multi-party dialogue contexts lead to challenges for dialogue reading comprehension, where multiple dialogue threads flow simultaneously within a common dialogue history, increasing difficulties in understanding a dialogue history for both human and machine. Previous studies mainly focus on utterance encoding methods with carefully designed features and pay inadequate attention to characteristic features of the structure of dialogues. We specially take dialogue structure factors into account and design a novel model for dialogue disentangling. Based on the fact that dialogues are constructed on successive participation of speakers and interactions between users of interest, we extract clues of speaker property and reference of users to model structural information of dialogues. The proposed method achieves new state-of-the-art on benchmark dataset and contributes to dialogue-related comprehension.