Machine Reading Comprehension Based on Clause Complex
The machine reading comprehension task requires the machine to answer relevant questions according to the context.Focused on extractive machine reading comprehension,this paper proposes a clause complex based ma-chine reading comprehension method.The naming structure relationship of clause complex is introduced to alleviate the difficult cases with clue elements or answer elements spreading across multiple punctuation sentences.The ex-perimental results show that the proposed method improves the EM of the whole model by 3.26%,and that for the difficult cases by 3.49%.
machine reading comprehensioncross-punctuationquestions and answersclause complex
NETL
NSTL
万方数据
维普
