Boosting Factual Correctness of Abstractive Summarization
Authors:
Preprint
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 firstly propose a Fact-Aware Summarization model, FASum, which extracts factual relations from the article and integrates this knowledge into the decoding process via neural graph computation. Then, we propose a Factual Corrector model, FC, that can modify abstractive summaries generated by any model to improve factual correctness. Empirical results show that FASum generates summaries with significantly higher factual correctness compared with state-of-the-art abstractive summarization systems, both under an independently trained factual correctness evaluator and human evaluation. And FC improves the factual correctness of summaries generated by various models via only modifying several entity tokens.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Evaluating the Factual Consistency of Abstractive Text Summarization2020
- Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports2020
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019
- Text Summarization with Pretrained Encoders2019
- SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing2018
- Bottom-Up Abstractive Summarization2018
- Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization2018
- Get To The Point: Summarization with Pointer-Generator Networks2017