Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehension

TL;DR

This paper introduces an enhanced speaker-aware model for multi-party multi-turn dialogue comprehension, utilizing masking attention and heterogeneous graph networks to better capture speaker-related discourse clues, leading to state-of-the-art results.

Contribution

The paper proposes a novel speaker-aware modeling approach with masking attention and heterogeneous graph networks, improving dialogue comprehension performance.

Findings

Achieves state-of-the-art results on Molweni dataset.

Enhances connections between utterances and speakers.

Effectively captures speaker-aware discourse relations.

Abstract

Multi-party multi-turn dialogue comprehension brings unprecedented challenges on handling the complicated scenarios from multiple speakers and criss-crossed discourse relationship among speaker-aware utterances. Most existing methods deal with dialogue contexts as plain texts and pay insufficient attention to the crucial speaker-aware clues. In this work, we propose an enhanced speaker-aware model with masking attention and heterogeneous graph networks to comprehensively capture discourse clues from both sides of speaker property and speaker-aware relationships. With such comprehensive speaker-aware modeling, experimental results show that our speaker-aware model helps achieves state-of-the-art performance on the benchmark dataset Molweni. Case analysis shows that our model enhances the connections between utterances and their own speakers and captures the speaker-aware discourse relations, which are critical for dialogue modeling.