Alleviating Exposure Bias in Abstractive Summarization via Sequentially Generating and Revising

Abstract

Abstractive summarization commonly suffers from exposure bias caused by supervised teacher-force learning, that a model predicts the next token conditioned on the accurate pre-context during training while on its preceding outputs at inference. Existing solutions bridge this gap through un- or semi-supervised holistic learning yet still leave the risk of error accumulation while generating a summary. In this paper, we attribute this problem to the limitation of unidirectional autoregressive text generation and introduce post-processing steps to alleviate it. Specifically, we reformat abstractive summarization to sequential generation and revision (SeGRe), i.e., a model in the revision phase re-inputs the generated summary and refines it by contrasting it with the source document. This provides the model additional opportunities to assess the flawed summary from a global view and thereby modify inappropriate expressions. Moreover, we train the SeGRe model with a regularized minimum-risk policy to ensure effective generation and revision. A lot of comparative experiments are implemented on two well-known datasets, exhibiting the new or matched state-of-the-art performance of SeGRe.