Tibetan Question Generation Based on Sequence to Sequence Model

作     者：Yuan Sun Chaofan Chen Andong Chen Xiaobing Zhao 

作者机构：School of Information EngineeringMinzu University of ChinaBeijing100081China Minority Languages BranchNational Language Resource and Monitoring Research Center Queen Mary University of LondonLondonE14NSUK 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2021年第68卷第9期

页      面：3203-3213页

核心收录：

学科分类：0302[法学-政治学] 03[法学] 030204[法学-中共党史(含：党的学说与党的建设)] 

基　　金：This work is supported by the National Nature Science Foundation(No.61972436) 

主　　题：Tibetan question generation copy mechanism attention 

摘      要：As the dual task of question answering,question generation(QG)is a significant and challenging task that aims to generate valid and fluent questions from a given *** QG task is of great significance to question answering systems,conversational systems,and machine reading comprehension *** sequence to sequence neural models have achieved outstanding performance in English and Chinese QG ***,the task of Tibetan QG is rarely *** key factor impeding its development is the lack of a public Tibetan QG *** with this challenge,the present paper first collects 425 articles from the Tibetan Wikipedia website and constructs 7,234 question–answer pairs through ***,we propose a Tibetan QG model based on the sequence to sequence framework to generate Tibetan questions from given ***,in order to generate answer-aware questions,we introduce an attention mechanism that can capture the key semantic information related to the ***,we adopt a copy mechanism to copy some words in the paragraph to avoid generating unknown or rare words in the ***,experiments show that our model achieves higher performance than baseline *** also further explore the attention and copy mechanisms,and prove their effectiveness through experiments.