STRUDEL: Structured Dialogue Summarization for Dialogue Comprehension

TL;DR

This paper introduces STRUDEL, a structured dialogue summarization method that enhances dialogue comprehension tasks by integrating summaries into a graph-based reasoning framework, significantly improving model performance.

Contribution

The paper proposes a novel structured dialogue summarization task, STRUDEL, and demonstrates its effectiveness in improving dialogue comprehension models using a graph neural network approach.

Findings

STRUDEL summaries improve dialogue question answering accuracy.

Integration of STRUDEL enhances dialogue response prediction.

Empirical results show significant performance gains on two tasks.

Abstract

Abstractive dialogue summarization has long been viewed as an important standalone task in natural language processing, but no previous work has explored the possibility of whether abstractive dialogue summarization can also be used as a means to boost an NLP system's performance on other important dialogue comprehension tasks. In this paper, we propose a novel type of dialogue summarization task - STRUctured DiaLoguE Summarization - that can help pre-trained language models to better understand dialogues and improve their performance on important dialogue comprehension tasks. We further collect human annotations of STRUDEL summaries over 400 dialogues and introduce a new STRUDEL dialogue comprehension modeling framework that integrates STRUDEL into a graph-neural-network-based dialogue reasoning module over transformer encoder language models to improve their dialogue comprehension abilities. In our empirical experiments on two important downstream dialogue comprehension tasks - dialogue question answering and dialogue response prediction - we show that our STRUDEL dialogue comprehension model can significantly improve the dialogue comprehension performance of transformer encoder language models.