Entity-based SpanCopy for Abstractive Summarization to Improve the Factual Consistency
This addresses factual errors in summarization for NLP applications, but it is incremental as it builds on existing methods.
The paper tackled the problem of factual inconsistencies in abstractive summarization by focusing on entity-level mismatches, and the proposed entity-based SpanCopy mechanism improved entity-level factual consistency across four datasets without affecting saliency.
Despite the success of recent abstractive summarizers on automatic evaluation metrics, the generated summaries still present factual inconsistencies with the source document. In this paper, we focus on entity-level factual inconsistency, i.e. reducing the mismatched entities between the generated summaries and the source documents. We therefore propose a novel entity-based SpanCopy mechanism, and explore its extension with a Global Relevance component. Experiment results on four summarization datasets show that SpanCopy can effectively improve the entity-level factual consistency with essentially no change in the word-level and entity-level saliency. The code is available at https://github.com/Wendy-Xiao/Entity-based-SpanCopy