面向高考阅读理解的句子语义相关度

郭少茹; 张虎; 钱揖丽; 李茹; 杨陟卓; 顾兆军; 马淑晖

doi:10.16511/j.cnki.qhdxxb.2017.26.021

PDF(1167 KB)

清华大学学报（自然科学版） ›› 2017, Vol. 57 ›› Issue (6) : 575-579,585. DOI: 10.16511/j.cnki.qhdxxb.2017.26.021

计算机科学与技术

面向高考阅读理解的句子语义相关度

郭少茹¹, 张虎¹, 钱揖丽¹, 李茹^1,2, 杨陟卓¹, 顾兆军³, 马淑晖¹

作者信息 +

Semantic relevancy between sentences for Chinese reading comprehension on college entrance examinations

GUO Shaoru¹, ZHANG Hu¹, QIAN Yili¹, LI Ru^1,2, YANG Zhizhuo¹, GU Zhaojun³, MA Shuhui¹

Author information +

文章历史 +

摘要

高考阅读理解选择题是基于背景材料，通过对材料的“理解”从多个选项中选出最佳选项。由于提供的背景材料相对较短且关键信息极具隐藏性，答案可能无法在背景材料中直接找到，因此从背景材料中挖掘信息并与选项进行相关性分析是解答该类问题的关键，而句子级的语义相关性分析是背景材料与选项相关性分析的基础。该文通过对大量高考科技文文意理解类选择题进行分析，提出基于多维度投票算法的句子语义相关度计算方法。该方法将不同维度的语义相关性作为度量标准，运用投票算法的思想，选取问题的最佳选项。在近十年北京市高考真题上进行测试，解答准确率为53.84%，验证了该方法的有效性。

Abstract

Multiple-choice reading comprehension questions in the Chinese College Entrance Examination are based on the given background material with the reader selecting the best option from a number of options. The answer may not be directly found in the background material since the passage is relatively short and the key information is hidden. Thus, information mining from the background material and semantic relevancy analyses with options are keys to solving the problem, with sentence level semantic relevancy analysis as the foundation. This paper presents an algorithm to calculate the semantic relevancy between sentences based on Multi-Dimension Voting by analyzing large numbers of multiple-choice questions from Chinese scientific article text understanding questions from college entrance examinations. The method utilizes the voting algorithm to take advantage of different size metrics to select the best option. The algorithm accuracy for the national college entrance examination of Beijing text understanding questions is 53.84%, which verifies the validity of the method.

导出引用

郭少茹, 张虎, 钱揖丽, 李茹, 杨陟卓, 顾兆军, 马淑晖. 面向高考阅读理解的句子语义相关度[J]. 清华大学学报（自然科学版）. 2017, 57(6): 575-579,585 https://doi.org/10.16511/j.cnki.qhdxxb.2017.26.021

GUO Shaoru, ZHANG Hu, QIAN Yili, LI Ru, YANG Zhizhuo, GU Zhaojun, MA Shuhui. Semantic relevancy between sentences for Chinese reading comprehension on college entrance examinations[J]. Journal of Tsinghua University(Science and Technology). 2017, 57(6): 575-579,585 https://doi.org/10.16511/j.cnki.qhdxxb.2017.26.021

中图分类号： TP391.1

参考文献

[1] 吴友政, 赵军, 段湘煜, 等. 问答式检索技术及评测研究综述[J]. 中文信息学报, 2005, 19(3):2-14. WU Youzheng, ZHAO Jun, DUAN Xiangyu, et al. Research on question answering & evaluation:A survey[J]. Journal of Chinese Information Processing, 2005, 19(3):2-14. (in Chinese) [2] Berant J, Chou A, Frostig R, et al. Semantic parsing on freebase from question-answer pairs[C]//Proceedings of EMNLP. Seattle, WA, USA:EMNLP, 2013:6-17. [3] Antoine Y B, Sumit C. Question answering with subgraph embeddings[C]//EMNLP. Doha, Qatar:EMNLP, 2014:615-620. [4] Ferrucci D, Brown E, Chu-Carroll J, et al. Building watson:An overview of the deep QA project[J]. AI Magazine, 2010, 31(3):59-79. [5] Zhang K, Wu W, Wang F, et al. Learning distributed representations of data in community question answering for question retrieval[C]//Ninth ACM International Conference on Web Search and Data Mining. Amsterdam, Holland:ACM Press, 2016:533-542. [6] 黄昌宁.从IBM深度问答系统战胜顶尖人类选手所想到的[J].中文信息学报, 2011, 25(6):21-25. HUANG Changning. Thinking about deep QA beating human champions[J]. Journal of Chinese Information Processing, 2011, 25(6):21-25. (in Chinese) [7] Richardson M, Burges C J C, Renshaw E. MCTest:A challenge dataset for the open-domain machine comprehension of text[C]//Proceedings of EMNLP. Seattle, WS, USA:EMNLP, 2013:193-203. [8] Narasimhan K, Barzilay R. Machine comprehension with discourse relations[C]//Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing. Beijing, China:ACL Press, 2015:1253-1262. [9] Sachan M, Dubey K, Xing E, et al. Learning answer-entailing structures for machine comprehension[C]//Meeting of the Association for Computational Linguistics and the, International Joint Conference on Natural Language Processing. Beijing, China:ACL Press, 2015:239-249. [10] Wang H, Bansal M, Gimpel K, et al. Machine comprehension with syntax, frames, and semantics[C]//Meeting of the Association for Computational Linguistics and the, International Joint Conference on Natural Language Processing. Beijing, China:ACL Press, 2015:700-706. [11] 刘群, 李素建. 基于《知网》的词汇语义相似度计算[J]. 中文计算语言学, 2002, 7(2):59-76.LIU Qun, LI Sujian. Word similarity computing based on how-net[J]. Computational Linguistics and Chinese Language Processing, 2002, 7(2):59-76. (in Chinese) [12] 郝晓燕, 刘伟, 李茹, 等. 汉语框架语义知识库及软件描述体系[J]. 中文信息学报, 2007, 21(5):96-100. HAO Xiaoyan, LIU Wei, LI Ru, et al. Description systems of the Chinese framenet database and software tools[J]. Journal of Chinese Information Processing, 2007, 21(5):96-100. (in Chinese) [13] Fillmore C J. Frame semantics and the nature of language[J]. Annals of the New York Academy of Sciences, 1976, 280(1):20-32. [14] Baker C F, Fillmore C J, Lowe J B. The Berkeley framenet project[C]//Annual Meeting of the Association for ComputationalLinguistics and 17th International Conference on Computational Linguistics-Volume 1. Montreal, Quebec, Canada:ACL Press, 1998:86-90. [15] Ruppenhofer J, Sporleder C, Morante R, et al. Semeval-2010 task 10:Linking events and their participants in discourse[C]//International Workshop on Semantic Evaluation. Uppsala, Sweden:ACL Press, 2010:45-50. [16] 李茹. 汉语句子框架语义结构分析技术研究[D]. 太原:山西大学, 2012. LI Ru. Research on Frame Semantic Structure Analysis Technology for Chinese Sentences[D]. Taiyuan:Shanxi University, 2012. (in Chinese) [17] Che W, Li Z, Liu T. LTP:A Chinese language technology platform[C]//International Conference on Computational Linguistics. Beijing, China:DBLP, 2010:13-16. [18] Dempster A P. Upper and lower probabilities induced by a multi-valued mapping[J]. Annals of Mathematical Statistics, 1967, 38(2):325-339. [19] Inglis J. A mathematical theory of evidence[J]. Technometrics, 1978, 20(1):242-242.

PDF(1167 KB)

Accesses

Citation

Detail

段落导航

收稿日期	出版日期
2016-12-15	2017-06-15
发布日期
2017-06-15

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

访问统计

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

访问统计