InforME: Improving Informativeness of Abstractive Text Summarization With Informative Attention Guided by Named Entity Salience
This addresses the problem of generating more informative summaries for efficient human consumption in the Big Data era, representing an incremental improvement over prior methods.
The paper tackled improving informativeness in abstractive text summarization by proposing a novel learning approach with optimal transport-based informative attention and accumulative joint entropy reduction on named entities, achieving better ROUGE scores on CNN/Daily Mail and competitive results on XSum.
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.