Boosting Factual Correctness of Abstractive Summarization with Knowledge Graph
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 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.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Evaluating the Factual Consistency of Abstractive Text Summarization2020
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization2020
- Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports2020
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019
- Neural Text Summarization: A Critical Evaluation2019
- 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
- A Neural Attention Model for Abstractive Sentence Summarization2015