Structural Characterization for Dialogue Disentanglement

TL;DR

This paper introduces a novel structural modeling approach for dialogue disentanglement that considers speaker roles and reference dependencies, significantly improving performance on benchmark datasets.

Contribution

It presents a new model that explicitly incorporates structural features like speaker properties and reference dependencies for better dialogue disentanglement.

Findings

Achieves state-of-the-art results on Ubuntu IRC dataset.

Highlights the importance of structural features in dialogue understanding.

Enhances dialogue comprehension by modeling interaction structures.

Abstract

Tangled multi-party dialogue contexts lead to challenges for dialogue reading comprehension, where multiple dialogue threads flow simultaneously within a common dialogue record, increasing difficulties in understanding the dialogue history for both human and machine. Previous studies mainly focus on utterance encoding methods with carefully designed features but pay inadequate attention to characteristic features of the structure of dialogues. We specially take structure factors into account and design a novel model for dialogue disentangling. Based on the fact that dialogues are constructed on successive participation and interactions between speakers, we model structural information of dialogues in two aspects: 1)speaker property that indicates whom a message is from, and 2) reference dependency that shows whom a message may refer to. The proposed method achieves new state-of-the-art on the Ubuntu IRC benchmark dataset and contributes to dialogue-related comprehension.