医学汉语水平考试对话流完形填空智能出题系统研究Research on an Intelligent Automatic Question Generation System for the Dialogue Completion Section of the Chinese Medical Language Proficiency Test
王华珍,孙雨洁,林致中,姜力文,佟丹丹,何霆
摘要(Abstract)：
针对医学汉语水平考试（Medical Chinese Test，简称MCT）题库建设成本高昂及资料匮乏等问题，本文提出MCT对话流完形填空智能出题系统研发思路，旨在通过智能化方法实现对话流的高效生成和完形填空题的挖空出题。该系统主要包括对话流智能生成和完形填空智能出题两部分。在对话流智能生成部分，该系统先依据电子病历构建知识图谱，再采用图神经网络实现基于知识图谱的问题与问题链的生成，从而获得对话流数据；在完形填空智能出题部分，该系统首先基于多维复杂医学约束知识对对话流文本进行篇章语义解析，筛选出符合要求的对话流作为出题语料，然后进行对话流文本的知识标注，最后完成挖空并生成干扰项。结果表明，该系统能够有效地生成大量MCT对话流完形填空题目，经人工检测与评估，所生成的题目质量较高。
关键词(KeyWords)： 医学汉语水平考试;MCT;智能出题系统;对话流生成;完形填空出题
基金项目(Foundation): 汉考国际科研基金项目“基于电子病历的MCT题库资源智能生成”（CTI2021B02）;; 华侨大学中央高校基本科研业务费资助项目（TZYB-202005）;; 福建省社会科学基金基础研究项目“基于智能语音模型的洋腔洋调评测与识别系统研究”（FJ2021B110）的研究成果
作者(Author): 王华珍,孙雨洁,林致中,姜力文,佟丹丹,何霆
参考文献(References)：
- 丁向民，顾宏斌.基于本体的中文多项选择题自动生成技术研究[J].计算机工程与设计，2010(6):1397-1400.
- 教育部语言交流合作中心.重磅！医学汉语水平考试（MCT）大纲正式发布[EB/OL].(2020-12-01)[2022-09-28].https://mp.weixin.qq.com/s/XLSkbasm5x6ow2XyDnmAxg.
- 乔振浩，车万翔，刘挺.基于问题生成的知识图谱问答方法[J].智能计算机与应用，2020(5):1-5.
- 张滨.对当前在线考试系统存在问题的分析与改进建议[J].佳木斯教育学院学报，2011(3):310.
- 张静，勾焕茹.基于职业教育国际合作云平台的智慧教学研究--以对外汉语教学为例[J].石家庄职业技术学院学报，2019(6):61-64.
- 赵新筠，周忠强，吴腊梅，等.超星学习通辅助分段考试在高校有机化学课程中的应用[J].大学化学，2019(7):47-51.
- 中华人民共和国教育部，国家语言文字工作委员会.国际中文教育中文水平等级标准（GF 0025-2021)[S].北京：北京语言大学出版社，2021.
- CHAN Y H,FAN Y C.A recurrent BERT-based model for question generation[C].In:FISCH A,TALMOR A,JIA R,et al.Proceedings of the 2nd Workshop on Machine Reading for Question Answering.Hong Kong:Association for Computational Linguistics,2019:154-162.
- GAO Y F,LI P J,KING I,et al.Interconnected question generation with coreference alignment and conversation flow modeling[R].Paper presented at the 57th Annual Meeting of the Association for Computational Linguistics(ACL),Florence,Italy,2019.
- HEILMAN M,SMITH N A.Extracting simplified statements for factual question generation[C].In:BOYER K E,PIWEK P.Proceedings of QG2010:The Third Workshop on Question Generation.Pittsburgh:questiongeneration.org.,2010.
- HUSAM A,CHALI Y,HASAN S A.Automatic question generation from sentences[C].In:BOYER K E,PIWEK P.Proceedings of QG2010:The Third Workshop on Question Generation.Pittsburgh:questiongeneration.org.,2010.
- KONCEL-KEDZIORSKI R,BEKAL D,LUAN Y,et al.Text generation from knowledge graphs with graph transformers[C].In:BURSTEIN J,DORAN C,SOLORIO T.Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Volume 1(Long and Short Papers).Minneapolis:Association for Computational Linguistics,2019:2284-2293.
- LI L N,WAN X J.Point precisely:towards ensuring the precision of data in generated texts using delayed copy mechanism[C].In:BENDER E M,DERCZYNSKI L,ISABELLE P.Proceedings of the 27th International Conference on Computational Linguistics.Santa Fe:Association for Computational Linguistics,2018:1044-1055.
- MANNEM P,PRASD R,JOSHI A.Question generation from paragraphs at UPenn:QGSTEC system description[C].In:BOYER K Z,PIWEK P.Proceedings of QG2010:The Third Workshop on Question Generation.Pittsburgh:questiongeneration.org.,2010.
- MEI H Y,BANSAL M,WALTER M R.What to talk about and how?Selective generation using LSTMs with coarse-to-fine alignment[C].In:KNIGHT K,NENKOVA A,RAMBOW O.Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.San Diego:Association for Computational Linguistics,2016:720-730.
- MITKOV R,HA L A.Computer-aided generation of multiple-choice tests[C].In:BURSTEIN J,LEACOCK C.Proceedings of the HLT-NAACL 03 Workshop on Building Educational Applications Using Natural Language Processing-Volume 2.Stroudsburg:Association for Computational Linguistics,2003:17-22.
- PAN B Y,LI H,YAO Z Y,et al.Reinforced dynamic reasoning for conversational Question Generation[R].Paper presented at the SIGNLL Conference on Computational Natural Language Learning(CoNLL) 2020,Virtual Conference,2020.
- PAPASALOUROS A,KANARIS K,KOTIS K.Automatic generation of multiple-choice questions from domain ontologies[C].In:NUNES M B,MC PHERSON M.Proceedings of IADIS Elearning 2008 Conference.Amsterdam:IADIS,2008.
- QI P,Zhang Y H,Manning C D.Stay hungry,stay focused:generating informative and specific questions in information-seeking conversations[R].Paper presented at the SIGNLL Conference on Computational Natural Language Learning (CoNLL)2020,Virtual Conference,2020.
- RUS V,WYSE B,PIWEK P,et al.The first question generation shared task evaluation challenge[C].In:KELLEHER J,MACNAMEE B,VAN DER SLUIS I.Proceedings of the 6th International Natural Language Generation Conference.Ireland:Association for Computational Linguistics,2010.
- SEE A,LIU P J,MANNING C D.Get to the point:summarization with pointer-generator networks[C].In:BARZILAY R,KANM-Y.Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).Vancouver:Association for Computational Linguistics,2017.
- SERBAN I V,SORDONI A,LOWE R,et al.A hierarchical latent variable encoder-decoder model for generating dialogues[C].In:SINGH S,MARKOVITCH S.Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence.San Francisco:AAAI Press,2017.
- ZHANG F,HU C,YIN Q,et al.Multi-aspect-aware bidirectional LSTM networks for synthetic aperture radar target recognition[J]IEEE Access,2017(5):26880-26891.