A key challenge for abstractive summarization is ensuring factual consistency of the generated summary with respect to the original document. For example, state-of-the-art models trained on existing datasets exhibit entity hallucination, generating names of entities that are not present in the source document. We propose a set of new metrics to quantify the entity-level factual consistency of generated summaries and we show that the entity hallucination problem can be alleviated by simply filtering the training data. In addition, we propose a summary-worthy entity classification task to the training process as well as a joint entity and summary generation approach, which yield further improvements in entity level metrics.
@article{arxiv.2102.09130,
title = {Entity-level Factual Consistency of Abstractive Text Summarization},
author = {Feng Nan and Ramesh Nallapati and Zhiguo Wang and Cicero Nogueira dos Santos and Henghui Zhu and Dejiao Zhang and Kathleen McKeown and Bing Xiang},
journal= {arXiv preprint arXiv:2102.09130},
year = {2021}
}