Bridging Hierarchical and Sequential Context Modeling for Question-driven Extractive Answer Summarization

Yang Deng, Wenxuan Zhang, Yaliang Li, Min Yang, Wai Lam, Ying Shen

Abstract

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.
BibTeX
@inproceedings{deng2020bridging,
  author = {Yang Deng and Wenxuan Zhang and Yaliang Li and Min Yang and Wai Lam and Ying Shen},
  title = {{Bridging Hierarchical and Sequential Context Modeling for Question-driven Extractive Answer Summarization}},
  booktitle = {International ACM SIGIR Conference on Research and Development in Information Retrieval},
  year = {2020},
  doi = {10.1145/3397271.3401208},
}

Loading related content...

Figure