Dialogue Summarization with Supporting Utterance Flow Modeling and Fact Regularization

TL;DR

This paper introduces an end-to-end neural dialogue summarization model with novel supporting utterance flow and fact regularization modules, improving coherence and factual accuracy, validated on new and existing datasets.

Contribution

It proposes two novel modules for dialogue summarization and introduces a new benchmark dataset, advancing the state-of-the-art in coherence and factual correctness.

Findings

Enhanced coherence through supporting utterance flow modeling

Improved factual accuracy with fact regularization

Effective on both existing and new datasets

Abstract

Dialogue summarization aims to generate a summary that indicates the key points of a given dialogue. In this work, we propose an end-to-end neural model for dialogue summarization with two novel modules, namely, the \emph{supporting utterance flow modeling module} and the \emph{fact regularization module}. The supporting utterance flow modeling helps to generate a coherent summary by smoothly shifting the focus from the former utterances to the later ones. The fact regularization encourages the generated summary to be factually consistent with the ground-truth summary during model training, which helps to improve the factual correctness of the generated summary in inference time. Furthermore, we also introduce a new benchmark dataset for dialogue summarization. Extensive experiments on both existing and newly-introduced datasets demonstrate the effectiveness of our model.