Coreference-Aware Dialogue Summarization

TL;DR

This paper explores methods to incorporate coreference information into neural dialogue summarization models, significantly improving their ability to produce accurate, coherent summaries by better understanding speaker interactions and information flow.

Contribution

It introduces explicit coreference-aware techniques into neural abstractive dialogue summarization, achieving state-of-the-art results and enhancing factual correctness.

Findings

Achieved state-of-the-art performance on dialogue summarization benchmarks.

Coreference-aware models better trace information flow among speakers.

Models show improved factual correctness in summaries.

Abstract

Summarizing conversations via neural approaches has been gaining research traction lately, yet it is still challenging to obtain practical solutions. Examples of such challenges include unstructured information exchange in dialogues, informal interactions between speakers, and dynamic role changes of speakers as the dialogue evolves. Many of such challenges result in complex coreference links. Therefore, in this work, we investigate different approaches to explicitly incorporate coreference information in neural abstractive dialogue summarization models to tackle the aforementioned challenges. Experimental results show that the proposed approaches achieve state-of-the-art performance, implying it is useful to utilize coreference information in dialogue summarization. Evaluation results on factual correctness suggest such coreference-aware models are better at tracing the information flow among interlocutors and associating accurate status/actions with the corresponding interlocutors and person mentions.