Hierarchical Sliding Inference Generator for Question-driven Abstractive Answer Summarization

作者：Bing Li, Peng Yang, Hanlin Zhao, Penghui Zhang, Zijian Liu · 发表于：ACM Transactions on Information Systems · 年份：2022 · DOI：10.1145/3511891 · 被引用次数：16 · 研究领域：Topic Modeling、Natural Language Processing Techniques、Advanced Graph Neural Networks

Text summarization on non-factoid question answering (NQA) aims at identifying the core information of redundant answer guidance using questions, which can dramatically improve answer readability and comprehensibility. Most existing approaches focus on extracting query-related sentences to construct a summary, where the logical connection of natural language and the hierarchical interpretable semantic association are often neglected, thus degrading performance. To address these issues, we propose a novel question-driven abstractive answer summarization model, called the H ierarchical S liding I nference G enerator (HSIG), to form inferable and interpretable summaries by explicitly introducing hierarchical information reasoning between questions and corresponding answers. Specifically, we first apply an elaborately designed hierarchical sliding fusion inference model to determine the most relevant question sentence-level representation that provides a deeper interpretable basis for sentence selection in summarization, which further increases computational performance on the premise of following the semantic inheritance structure. Additionally, to improve summary fluency, we construct a double-driven selective generator to integrate various semantic information from two mutual question-and-answer perspectives. Experimental results illustrate that compared with state-of-the-art baselines, our model achieves remarkable improvement on two benchmark datasets and specifically improv...