基于认知概念的谓词扩展与表示

doi:10.3969/j.issn.2095-2198.2022.06.017

摘要
参考文献
相关文章
推荐阅读
Metrics

下载:

PDF (428KB)
输出: BibTeX | EndNote (RIS)

摘要

语义分析是将自然语言转换成为计算机可处理的谓词逻辑形式.由于谓词公式中仅包含客体和谓词两部分，不能完整、精确地表达自然语言语句的语义，限制了语义分析技术的广泛应用，因此需要对谓词进行改进.根据“符号学三角形”语义理论，自然语言和谓词逻辑作为符号系统，反映的都是现实世界在头脑中形成的概念.以认知概念为指导扩展谓词逻辑，增加谓词修饰元素和复杂客体，以提高谓词公式的表达能力.同时规范汉语词类、语法成分和句子结构到谓词公式组成元素间的对应关系和转换方法，保证谓词公式正确表达语句的语义.利用包含各种词类和短语作语法成分的汉语语句实例进行验证和分析，结果表明，对谓词的扩展和转换过程的规范，提高了谓词公式对汉语语句语义表达的完整和准确性，为更广泛深入地语义分析奠定了基础.

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	（）
	作者相关文章

关键词: 认知概念')" href="#">

认知概念谓词扩展复杂客体谓词修饰语法结构语义分析

Abstract:

Semantic parsing converts natural language into predicate logic form that can be executed by computer.A predicate formula only contains two parts:predicate and variable.It cannot express a sentence meaning in a complete and accurate way，which limits the wide applications of semantic paring.So an improvement of predicate is required.According to the theory of “Semiotic Triangle”，as symbol systems，natural language and predicate logic are both used to symbolize concepts of the world in our brain.Using cognition concepts to extend predicate logic，adding predicate modifier and complex variable improved the representation ability of predicate formulas.Specifying the corresponding relations and converting method between Chinese word types，grammatical elements，sentence structures and predicate formula elements ensured predicate formulas express sentence meaning correctly.Experiments and verifications were carried out using Chinese sentences with various kind of word types and phrases as grammatical components.The results showed that extended predicate and specified converting process improved the integrity and accuracy of predicate formulas when representing Chinese sentence meaning.This provided a foundation for further research in semantic parsing.

Key words: cognition concept')" href="#">

cognition concept predicate extension complex variable predicate modifier Chinese grammatical structure semantic parsing

出版日期: 2022-12-31 发布日期: 2024-06-06 整期出版日期: 2022-12-31

ZTFLH:

TP391

引用本文:

唐忠, 刘华阳, 刘珊珊, 李大舟.

基于认知概念的谓词扩展与表示 [J]. 沈阳化工大学学报, 2022, 36(6): 569-576.
TANG Zhong, LIU Hua-yang, LIU Shan-shan, LI Da-zhou.

Extension and Representation of Predicate Logic Based on Cognition Concept . Journal of Shenyang University of Chemical Technology, 2022, 36(6): 569-576.

链接本文:

https://xuebao.syuct.edu.cn/CN/10.3969/j.issn.2095-2198.2022.06.017 或 https://xuebao.syuct.edu.cn/CN/Y2022/V36/I6/569

［1］KAMATH A，DAS R.A Survey on Semantic Parsing［DB/OL］.（2019-05-29）［2020-05-10］.https://arxiv.org/abs/1812.00978.

［2］ARTZI Y，FITZGERALD N，ZETTLEMOYER L.Semantic Parsing with Combinatory Categorial Grammars［C］//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing：Tutorial Abstracts.Doha:Association for Computational Linguistics，2014:D14-2003.［3］KRISHNAMURTHY J，DASIGI P，GARDNER M.Neural Semantic Parsing with Type Constraints for Semi-structured Tables［C］//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.Copenhagen:Association for Computational Linguistics，2017:1516-1526.

［4］TAYAL M A，RAGHUWANSH M M，MALIK L.Knowledge Representation:Predicate Logic Implementation Using Sentence-Type for Natural Languages［C］//2013 International Conference on Circuits，Power and Computing Technologies(ICCPCT).Nagercoil:IEEE，2013:1264-1269.

［5］MPAGOULI A，HATZILYGEROUDIS I.Converting First Order Logic into Natural Language:a First Level Approach［C］//11th Panhellenic Conference in Informatics.Patras:PCI，2007:517-526.［6］LIANG P.Learning Executable Semantic Parsers for Natural Language Understanding［J］.Communications of the ACM，2016，59(9):68-76.

［7］ZHANG Y C，PASUPAT P，LIANG P.Macro Grammars and Holistic Triggering for Efficient Semantic Parsing［C］//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.Copenhagen:Association for Computational Linguistics，2017:1214-1223.

［8］SAPAROV A，SARASWAT V，MITCHELL T.A Probabilistic Generative Grammar for Semantic Parsing［C］//Proceedings of the 21st Conference on Computational Natural Language Learning（CoNLL 2017）.Vancouver:Association for Computational Linguistics，2017:248-259.

［9］LIANG C，BERANT J，LE Q，et al.Neural Symbolic Machines:Learning Semantic Parsers on Freebase with Weak Supervision［C］//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics （Volume 1：Long Papers）.Vancouver:Association for Computational Linguistics，2017:23-33.

［10］REBELE T，SUCHANEK F，HOFFART J，et al.YAGO:A Multilingual Knowledge Base from Wikipedia，Wordnet，and Geonames［C］//The Semantic Web-ISWC 2016.Cham： Springer，2016:177-185.

［11］DU X Y，CARDIE C.Harvesting Paragraph-Level Question-Answer Pairs from Wikipedia［C］//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics（Volume 1：Long Papers）.Melbourne:Association for Computational Linguistics，2018:1907-1917.

［12］KRISHNAMURTHY J，MITCHELL T M.Weakly Supervised Training of Semantic Parsers［C］//Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning.Jeju Island:Association for Computational Linguistics，2012:754-765.

［13］CHOI E，KWIATKOWSKI T，ZETTLEMOYER L.Scalable Semantic Parsing with Partial Ontologies［C］//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing（Volume 1：Long Papers）.Beijing:Association for Computational Linguistics，2015:1311-1320.

［14］伍谦光.语义学导论［M］.长沙:湖南教育出版社，1991:75-81.

［15］韩荔华.实用现代汉语教程［M］.北京:旅游教育出版社，2002:187-431.

[1]	张翔宇, 朱立军. 改进的Faster R-CNN海洋鱼类检测模型 [J]. 沈阳化工大学学报, 2022, 36(6): 562-568.
[2]	张伟, 王倚天. 基于高频RFID的移动端图书自助借还系统设计与实现 [J]. 沈阳化工大学学报, 2022, 36(5): 476-480.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Shared

Discussed