Paper ID | HLT-4.1 | ||
Paper Title | PARAGRAPH LEVEL MULTI-PERSPECTIVE CONTEXT MODELING FOR QUESTION GENERATION | ||
Authors | Jun Bai, Wenge Rong, Feiyu Xia, Beihang University, China; Yanmeng Wang, Ping An Technology, China; Yuanxin Ouyang, Zhang Xiong, Beihang University, China | ||
Session | HLT-4: Dialogue Systems 2: Response Generation | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 14:00 - 14:45 | ||
Presentation Time: | Tuesday, 08 June, 14:00 - 14:45 | ||
Presentation | Poster | ||
Topic | Human Language Technology: [HLT-DIAL] Discourse and Dialog | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | Proper understanding of paragraph is essential for question generation task since the semantic interaction is complicated among sentences. How to integrate long text paragraph information into question generation is still a challenge. In this research, we proposed a multi-perspective paragraph context modeling mechanism, which firstly encodes the contextualized representation of input paragraph, and then utilize multi-head self-attention and Rezero network to further enhance paragraph-level feature extraction and context modeling. Finally, attention-based decoder with copy mechanism generates question according to encoded hidden states. Experimental study on widely used SQuAD dataset has shown the proposed method's potential. |