Key-Elements Graph Constructed with Evidence Sentence Extraction for Gaokao Chinese
Multiple choice questions from university admission exams(Gaokao in Chinese)is a challenging AI task since it requires effective representation to capture complicated semantic relations between sen-tences in the article and strong ability to handle long text.Face the above challenges,we propose a key-elements graph to enhance context semantic representation and a comprehensive evidence extraction method inspired by existing methods.Our model first extracts evidence sentences from a passage according to the corresponding question and options to reduce the impact of noise.Then combines syntactic analysis techniques with graph neural network to construct the key-elements graph bases on the extracted sentences.Finally,fusing the learned graph nodes represen-tation into context representation to enhancing syntactic information.Experiments on Gaokao Chinese multiple-choice dataset demonstrate the proposed model obtains substantial performance gains over various neu-ral model baselines in terms of accuracy.
Multiple-choice reading comprehension Evidence sentence extraction Graph neural network
Xiaoyue Wang Yu Ji Ru Li
School of Computer and Information Technology,Shanxi University,Taiyuan,China School of Computer and Information Technology,Shanxi University,Taiyuan,China;Key Laboratory of Comp
国际会议
9th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2020)
郑州
英文
1254-1265
2020-10-14（万方平台首次上网日期，不代表论文的发表时间）