Improving Factual Error Correction for Abstractive Summarization via Data Distillation and Conditional-generation Cloze
This addresses factual inconsistency in abstractive summarization, which is a critical issue for NLP applications, but the approach is incremental as it builds on post-editing methods.
The paper tackled factual errors in abstractive summarization by proposing FactCloze, a conditional-generation cloze model, and SummDSC, a data distillation method, resulting in improved factual consistency metrics compared to baselines.
Improving factual consistency in abstractive summarization has been a focus of current research. One promising approach is the post-editing method. However, previous works have yet to make sufficient use of factual factors in summaries and suffers from the negative effect of the training datasets. In this paper, we first propose a novel factual error correction model FactCloze based on a conditional-generation cloze task. FactCloze can construct the causality among factual factors while being able to determine whether the blank can be answered or not. Then, we propose a data distillation method to generate a more faithful summarization dataset SummDSC via multiple-dimensional evaluation. We experimentally validate the effectiveness of our approach, which leads to an improvement in multiple factual consistency metrics compared to baselines.