Entity-level Factual Consistency of Abstractive Text Summarization
105 Citations•2021•
Nan Feng, Ramesh Nallapati, Zhiguo Wang
journal unavailable
A set of new metrics are proposed to quantify the entity-level factual consistency of generated summaries and it is shown that the entity hallucination problem can be alleviated by simply filtering the training data.
Abstract
Feng Nan, Ramesh Nallapati, Zhiguo Wang, Cicero Nogueira dos Santos, Henghui Zhu, Dejiao Zhang, Kathleen McKeown, Bing Xiang. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.