Constructing of ATHowNet: A Semantic Knowledge Base for Aviation Terms

doi:10.12339/j.issn.1673-8578.2021.03.004

Abstract

Abstract:

Semantic knowledge base plays an important role in many areas of natural language processing. Existing semantic knowledge bases are produced mainly for common sense knowledge, and there is few semantic knowledge base for specific domains. This paper extends the theory and concept representation method of HowNet to the aviation domain, proposes a semantic knowledge base for aviation terms, ATHowNet, and describe the process of constructing it. This knowledge base contains 3700 concepts, 3959 relations and 3864 terms. ATHowNet is applied and verified in the task of aviation term similarity calculation and word analogy. The results show that ATHowNet is effective in aviation domain concept description and reasoning based on concept relationship.

Key words: semantic knowledge base, aviation terms, concept, concept relation

CLC Number:

N04
N949

WANG Peiyan, ZHANG Guiping, CAI Dongfeng. Constructing of ATHowNet: A Semantic Knowledge Base for Aviation Terms[J]. China Terminology, 2021, 23(3): 26-32.

Figures/Tables 7

References 22

[1]	董振东, 董强. 知网[Z/OL].[2021-05-07]. http://www.keenage.com/zhiwang/c_zhiwang.html.
[2]	BLOOMFIELD L. A set of postulates for the science of language[J]. Language, 1926,2(3):153-164. doi: 10.2307/408741 URL
[3]	LIU Q, LI S J. Word similarity computing based on how-net[J]. CLCLP, 2002,7(2):59-76.
[4]	FU X H, GUO L, GAO Y Y, et al. Multi-aspect sentiment analysis for chinese online social reviews based on topic modeling and hownet lexicon[J]. Knowledge-Based Systems, 2013,37(2):186-195. doi: 10.1016/j.knosys.2012.08.003 URL
[5]	NIU Y L, XIE R B, YUAN X C, et al. Improved word representation learning with sememes[C]// Association of Computational Linguistics.Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017: 2049-2058.
[6]	XIE R B, YUAN X C, LIU Z Y, et al. Lexical sememe prediction via word embeddings and matrix factorization[C]// International Joint Conferences on Artificial Intelligence Organization.Proceeding of the 26th International Joint Conference on Artificial Intelligence, 2017: 4200-4206.
[7]	GU Y H, YAN J, ZHU H, et al. Language modeling with sparse product of sememe experts[C]// Association for Computational Linguistics.Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018: 4642-4651.
[8]	QI F C, YANG C H, LIU Z Y, et al. Openhownet: An open sememe-based lexical knowledge base[J/OL] .[2021-05-07]. CoRR,abs/1901.09957. 2019.
[9]	CHEN K J, HUANG S L, SHIH Y Y, et al. Extended-HowNet: A representational framework for concepts[C]// Asian Federation of Natural Language Processing.Proceedings of OntoLex 2005-Ontologies and Lexical Resources, 2005.
[10]	SHIH Y Y, MA W Y . Extended hownet 2.0-an entity-relation common-sense representation model[C]// European Language Resources Association. Proceeding of the 11th International Conference on Language Resources and Evaluation Conference, 2018.
[11]	王莹莹, 白宇, 丁长林, 等. 面向语义检索的中医理论知识库构建方法的研究[J]. 中文信息学报, 2012,26(5):72-78.
[12]	张桂平, 刁丽娜, 王裴岩. 基于HowNet的航空术语语义知识库的构建[J]. 中文信息学报, 2014,28(5):92-101.
[13]	王羊羊, 陈刚, 蔡东风, 等. 基于HowNet的术语语义知识库构建技术[J]. 沈阳航空航天大学学报, 2016,33(4):78-84.
[14]	MIKOLOV T, CORRADO G, CHEN K, et al. Efficient Estimation of Word Representations in Vector Space[C]// Proceedings of the 1st International Conference on Learning Representations, 2013.
[15]	《中国航空百科词典》编辑部. 中国航空百科词典[M]. 北京: 航空工业出版社, 2000.
[16]	KDML:知网知识系统描述语言[Z/OL].[2021-05-07]. http://www.keenage.com/TheoryandpracticeofHowNet/07.pdf.
[17]	COHEN J. A coefficient of agreement for nominal scales[J]. Educational & Psychological Measurement, 1960,20(1):37-46.
[18]	STUDENT. Probable error of a correlation coefficient[J]. Biometrika, 1908,6(2/3):302-310. doi: 10.1093/biomet/6.2-3.302 URL
[19]	XIA T. Study on chinese words semantic similarity computation[J]. Computer Engineering, 2007,33(6):191-194. doi: 10.1007/s00366-016-0464-z URL
[20]	NIU Y L, XIE R B, YUAN X C, et al. Improved word representation learning with sememes[C]// Association for Computational Linguistics. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017: 2049-2058.
[21]	DEVLIN J, CHANG M W, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]// Association for Computational Linguistics.Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies, 2019: 4171-4186.
[22]	SONG Y, SHI S M, LI J, et al. Directional skip-gram: Explicitly distinguishing left and right context for word embeddings[C]// Association for Computational Linguistics.Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,NAACL-HLT, 2018: 175-180.

类别	术语数量
飞行器	170
飞行原理	203
飞行器结构设计与强度	234
推进技术与航空发动机	383
飞行控制、导航、显示/控制和记录系统	294
航空电子与计算机技术	521
航空机电系统	383
机载武器系统	381
航空安全、生命保障与航空医学	294
航空材料	302
航空制造工程	311
飞行、飞行试验与测试技术	388
总量	3864

类别	术语数量
飞行器	170
飞行原理	203
飞行器结构设计与强度	234
推进技术与航空发动机	383
飞行控制、导航、显示/控制和记录系统	294
航空电子与计算机技术	521
航空机电系统	383
机载武器系统	381
航空安全、生命保障与航空医学	294
航空材料	302
航空制造工程	311
飞行、飞行试验与测试技术	388
总量	3864

术语1	术语2	人工标注	自动计算
间隔标准	技术方案评价标准	0.1015	0.0944
	质量管理	-0.2493	-0.2656
	工程管理标准	-0.0342	-0.0256
通用飞机	鸭式飞机	0.2425	0.2544
	超轻型飞机	0.3265	0.3344
	复杂气象飞行	-0.548	-0.2656

术语1	术语2	人工标注	自动计算
间隔标准	技术方案评价标准	0.1015	0.0944
	质量管理	-0.2493	-0.2656
	工程管理标准	-0.0342	-0.0256
通用飞机	鸭式飞机	0.2425	0.2544
	超轻型飞机	0.3265	0.3344
	复杂气象飞行	-0.548	-0.2656