Bridging hierarchical and sequential context modeling for question-driven extractive answer summarization

• Main Authors: DENG, Yang, ZHANG, Wenxuan, LI, Yaliang, YANG, Min, LAM, Wai, SHEN, Ying
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Context modeling; Factoid questions; Multi-level interactions; On currents; Question Answering; Sentence level; Unified Modeling; Word level; Databases and Information Systems; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/9100; https://ink.library.smu.edu.sg/context/sis_research/article/10103/viewcontent/Bridging_Hierarchical_and_Sequential_Context_Modeling_for_Question_driven_Extractive_Answer_Summarization.pdf
• Institution: Singapore Management University

Non-factoid question answering (QA) is one of the most extensive yet challenging application and research areas of retrieval-based question answering. In particular, answers to non-factoid questions can often be too lengthy and redundant to comprehend, which leads to the great demand on answer sumamrization in non-factoid QA. However, the multi-level interactions between QA pairs and the interrelation among different answer sentences are usually modeled separately on current answer summarization studies. In this paper, we propose a unified model to bridge hierarchical and sequential context modeling for question-driven extractive answer summarization. Specifically, we design a hierarchical compare-aggregate method to integrate the interaction between QA pairs in both word-level and sentence-level into the final question and answer representations. After that, we conduct the question-aware sequential extractor to produce a summary for the lengthy answer. Experimental results show that answer summarization benefits from both hierarchical and sequential context modeling and our method achieves superior performance on WikiHowQA and PubMedQA.