With a Little Help from my (Linguistic) Friends: Topic Segmentation of Multi-party Casual Conversations
This work addresses the challenge of topic segmentation in open-domain conversations for researchers in dialogue analysis, though it appears incremental as it matches existing methods rather than surpassing them.
The paper tackles the problem of segmenting multi-party casual conversations into topically coherent sets of utterances, aiming to understand dialogue structure beyond utterance sequences, and achieves a comparable level of accuracy to recent machine learning models using a formal approach.
Topics play an important role in the global organisation of a conversation as what is currently discussed constrains the possible contributions of the participant. Understanding the way topics are organised in interaction would provide insight on the structure of dialogue beyond the sequence of utterances. However, studying this high-level structure is a complex task that we try to approach by first segmenting dialogues into smaller topically coherent sets of utterances. Understanding the interactions between these segments would then enable us to propose a model of topic organisation at a dialogue level. In this paper we work with open-domain conversations and try to reach a comparable level of accuracy as recent machine learning based topic segmentation models but with a formal approach. The features we identify as meaningful for this task help us understand better the topical structure of a conversation.