Who did They Respond to? Conversation Structure Modeling using Masked Hierarchical Transformer

Understand

Conversation structure is useful for both understanding the nature of conversation dynamics and for providing features for many downstream applications such as summarization of conversations.

• In this work, we define the problem of conversation structure modeling as identifying the parent utterance(s) to which each utterance in the conversation responds to.
• Previous work usually took a pair of utterances to decide whether one utterance is the parent of the other.
• We believe the entire ancestral history is a very important information source to make accurate prediction.