English

Entity-level Factual Consistency of Abstractive Text Summarization

Computation and Language 2021-02-19 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@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}
}

Comments

EACL 2021

R2 v1 2026-06-23T23:16:26.371Z