Abstractive Dialog Summarization with Semantic Scaffolds

Lin Yuan, Zhou Yu

Keywords: Abstractive Summarization, Dialog, Multi-task Learning

TL;DR: We propose a novel end-to-end model (SPNet) to incorporate semantic scaffolds for improving abstractive dialog summarization.

Abstract: The demand for abstractive dialog summary is growing in real-world applications. For example, customer service center or hospitals would like to summarize customer service interaction and doctor-patient interaction. However, few researchers explored abstractive summarization on dialogs due to the lack of suitable datasets. We propose an abstractive dialog summarization dataset based on MultiWOZ. If we directly apply previous state-of-the-art document summarization methods on dialogs, there are two significant drawbacks: the informative entities such as restaurant names are difficult to preserve, and the contents from different dialog domains are sometimes mismatched. To address these two drawbacks, we propose Scaffold Pointer Network (SPNet) to utilize the existing annotation on speaker role, semantic slot and dialog domain. SPNet incorporates these semantic scaffolds for dialog summarization. Since ROUGE cannot capture the two drawbacks mentioned, we also propose a new evaluation metric that considers critical informative entities in the text. On MultiWOZ, our proposed SPNet outperforms state-of-the-art abstractive summarization methods on all the automatic and human evaluation metrics.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:1910.00825/code)