Factual Relation Discrimination for Factuality-oriented Abstractive Summarization

Zhiguang Gao, PEIFENG LI, Feng Jiang, Xiaomin Chu, Qiaoming Zhu

Submission Type: Regular Long Paper

Submission Track: Summarization

Submission Track 2: NLP Applications

Keywords: Factuality-oriented Abstractive Summarization, Factual Relation Discrimination

TL;DR: Using factual relation discrimination for factuality-oriented abstractive summarization

Abstract: Most neural abstractive summarization models are capable of producing high-quality summaries. However, they still frequently contain factual errors. Existing factuality-oriented abstractive summarization models only consider the integration of factual information and ignore the causes of factual errors. To address this issue, we propose a factuality-oriented abstractive summarization model DASum, which is based on a new task factual relation discrimination that is able to identify the causes of factual errors. First, we use data augmentation methods to construct counterfactual summaries (i. e., negative samples), and build a factual summarization dataset. Then, we propose the factual relation discrimination task, which determines the factuality of the dependency relations in summaries during summary generation and guides our DASum to generate factual relations, thereby improving the factuality of summaries. Experimental results on the CNN/DM and XSUM datasets show that our DASum outperforms several state-of-the-art benchmarks in terms of the factual metrics.

Submission Number: 1302