通过实体重要性引导注意力，提升摘要信息量。
InforME: Improving Informativeness of Abstractive Text Summarization With Informative Attention Guided by Named Entity Salience
- 用最优传输方法聚焦参考摘要中的关键信息
- 通过命名实体联合熵减少，增强重要实体的显性
- 在CNN/Daily Mail上超越基线，人评信息量更优
抽象文本摘要在大数据时代至关重要，需将海量长文本转化为简洁连贯且信息丰富的摘要以支持高效阅读。尽管已有显著进展，但在信息量方面仍有提升空间。本文提出一种新学习方法，包含两项技术：基于最优传输的有信息量注意力机制，用于强化参考摘要中的核心信息学习；以及针对命名实体的累积联合熵减小方法，以提升其信息重要性。实验表明，在CNN/Daily Mail数据集上，该方法优于先前工作，取得更高ROUGE分数；在XSum上表现具有竞争力。人工评估进一步验证了其在信息量上的优越性。深入分析揭示了评估结果背后的原因。
原文摘要 · Abstract (English)
Abstractive text summarization is integral to the Big Data era, which demands advanced methods to turn voluminous and often long text data into concise but coherent and informative summaries for efficient human consumption. Despite significant progress, there is still room for improvement in various aspects. One such aspect is to improve informativeness. Hence, this paper proposes a novel learning approach consisting of two methods: an optimal transport-based informative attention method to improve learning focal information in reference summaries and an accumulative joint entropy reduction method on named entities to enhance informative salience. Experiment results show that our approach achieves better ROUGE scores compared to prior work on CNN/Daily Mail while having competitive results on XSum. Human evaluation of informativeness also demonstrates the better performance of our approach over a strong baseline. Further analysis gives insight into the plausible reasons underlying the evaluation results.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。