Regularizing Output Distribution of Abstractive Chinese Social Media Text Summarization for Improved Semantic Consistency

TL;DR

This paper introduces a regularization method for sequence-to-sequence models in Chinese social media text summarization, significantly enhancing semantic consistency of generated summaries compared to existing models.

Contribution

It proposes a novel regularization approach leveraging model knowledge and a human evaluation method to better assess semantic consistency in summaries.

Findings

Improves semantic consistency by 4% in human evaluation.

Outperforms most existing models in summarization tasks.

Enhances the alignment between source content and summaries.

Abstract

Abstractive text summarization is a highly difficult problem, and the sequence-to-sequence model has shown success in improving the performance on the task. However, the generated summaries are often inconsistent with the source content in semantics. In such cases, when generating summaries, the model selects semantically unrelated words with respect to the source content as the most probable output. The problem can be attributed to heuristically constructed training data, where summaries can be unrelated to the source content, thus containing semantically unrelated words and spurious word correspondence. In this paper, we propose a regularization approach for the sequence-to-sequence model and make use of what the model has learned to regularize the learning objective to alleviate the effect of the problem. In addition, we propose a practical human evaluation method to address the problem that the existing automatic evaluation method does not evaluate the semantic consistency with the source content properly. Experimental results demonstrate the effectiveness of the proposed approach, which outperforms almost all the existing models. Especially, the proposed approach improves the semantic consistency by 4\% in terms of human evaluation.