Boosting Factual Correctness of Abstractive Summarization with Knowledge Graph

Authors:

Abstract
A commonly observed problem with abstractive summarization is the distortion or fabrication of factual information in the article. This inconsistency between summary and original text has led to various concerns over its applicability. In this paper, we propose a Fact-Aware Summarization model, FASum, which extracts factual relations from the article to build a knowledge graph and integrates it into the neural decoding process. Then, we propose a Factual Corrector model, FC, that can modify abstractive summaries generated by any summarization model to improve factual correctness. Empirical results show that FASum can generate summaries with higher factual correctness compared with state-of-the-art abstractive summarization systems. And FC improves the factual correctness of summaries generated by various models via only modifying several entity tokens.