基于模式和投影学习的领域概念上下位关系自动识别研究
Automatically Identifying Hypernym-Hyponym Relations of Domain Concepts with Patterns and Projection Learning
查看参考文献31篇
|
文摘
|
【目的】实现对领域概念上下位关系的自动识别,以解决领域本体自动化构建中领域概念间语义关系的自动获取和确立问题。【方法】将传统无监督的基于模式的方法和当前先进的有监督的基于投影学习的方法有机结合起来,应用于领域概念上下位关系自动识别,并进行了实验研究。【结果】能识别出领域概念的上位词集合,在医学领域的识别精度为0.88,通用领域的识别精度为0.83,在评估基准集BLESS上的平均精度为0.85。【局限】受句法歧义、语料集质量等影响,模型精度尚未达到峰值,存在错误识别的情况。【结论】可发现同一概念词的不同意义的上位词,对低频词和命名实体也具有较好识别效果。未来可考虑从对高频顶层上位词进行适当减权、提升有监督语料集的质量等方面进行优化。 |
|
其他语种文摘
|
[Objective] This paper tries to automatically identify the hypernym-hyponym relations of domain concepts and establish their ontology. [Methods] First, we combined the traditional unsupervised pattern-based method and the advanced supervised-based projection learning method to automatically extract domain concepts. Then, we examined our new method with an empirical study. [Results] The proposed method could identify the hypernym sets of domain concepts. The identification accuracy in medical and general fields, as well as with the benchmark dataset BLESS were 0.88, 0.83, and 0.85 respectively. [Limitations] More research is needed to reduce the weight of high-frequency top-level words and improve the corpus quality. There are also some misidentified relationships. [Conclusions] The proposed model could find hypernym with different meanings for the same concept, which could also extract low-frequency words and named entities. |
|
来源
|
数据分析与知识发现
,2020,4(11):15-25 【扩展库】
|
|
DOI
|
10.11925/infotech.2096-3467.2020.0299
|
|
关键词
|
Hearst模式
;
投影学习
;
词嵌入
;
上下位关系
;
领域概念
|
|
地址
|
1.
中国科学院西北生态环境资源研究院文献情报中心, 兰州, 730000
2.
中国科学院大学, 北京, 100049
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
2096-3467 |
|
学科
|
社会科学总论;自动化技术、计算机技术 |
|
基金
|
国家科技部重点研发计划课题
;
中国科学院2019年西部之光项目
;
中国科学院西北生态环境资源研究院文献情报中心2018年文献情报创新能力建设项目
|
|
文献收藏号
|
CSCD:6853463
|
参考文献 共
31
共2页
|
|
1.
.
WordNet-A Lexical Database for English,2019
|
被引
1
次
|
|
|
|
|
2.
.
Cyc: Logical Reasoning with the World's Largest Knowledge Base,2019
|
被引
1
次
|
|
|
|
|
3.
程韵如. 基于维基百科的领域实体上下位关系抽取.
价值工程,2016,35(18):160-163
|
被引
1
次
|
|
|
|
|
4.
唐恩博.
基于WordNet的蒙古文名词语义网上下位语义关系树构造方法的研究,2014
|
被引
1
次
|
|
|
|
|
5.
Gunawan. Acquisition of Hypernymy-Hyponymy Relation Between Nouns for WordNet Building.
Proceedings of the 2010 International Conference on Asian Language Processing,2010:114-117
|
被引
1
次
|
|
|
|
|
6.
Hearst M A. Automatic Acquisition of Hyponyms from Large Text Corpora.
Proceedings of the 14th International Conference on Computational Linguistics. 2,1992:539-545
|
被引
2
次
|
|
|
|
|
7.
Roller S. Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment.
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing,2016:2163-2172
|
被引
1
次
|
|
|
|
|
8.
刘磊. 一种基于"是一个"模式的下位概念获取方法.
计算机科学,2006,33(9):146-151
|
被引
11
次
|
|
|
|
|
9.
汤青. 本体概念间上下位关系抽取研究.
微电子学与计算机,2014(6):68-71
|
被引
8
次
|
|
|
|
|
10.
Geffet M. The Distributional Inclusion Hypotheses and Lexical Entailment.
Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics,2005:107-114
|
被引
2
次
|
|
|
|
|
11.
Kotlerman L. Directional Distributional Similarity for Lexical Inference.
Natural Language Engineering,2010,16(4):359-389
|
被引
5
次
|
|
|
|
|
12.
Baroni M. How We BLESSed Distributional Semantic Evaluation.
Proceedings of the GEMS 2011 Workshop on Geometrical Models of Natural Language Semantics,2011:1-10
|
被引
4
次
|
|
|
|
|
13.
Mei K W. A Multi-Phase Correlation Search Framework for Mining Non-Taxonomic Relations from Unstructured Text.
Knowledge and Information Systems,2014,38(3):641-667
|
被引
2
次
|
|
|
|
|
14.
Roller S. Inclusive Yet Selective: Supervised Distributional Hypernymy Detection.
Proceedings of the 25th International Conference on Computational Linguistics,2014:1025-1036
|
被引
3
次
|
|
|
|
|
15.
Mikolov T. Efficient Estimation of Word Representations in Vector Space.
arXiv: 1301.3781
|
被引
50
次
|
|
|
|
|
16.
Pennington J.
GloVe: Global Vectors for Word Representation,2018
|
被引
6
次
|
|
|
|
|
17.
Peters M. Deep Contextualized Word Representations.
arXiv: 1802.05365
|
被引
2
次
|
|
|
|
|
18.
Devlin J. BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding.
arXiv: 1810.04805
|
被引
42
次
|
|
|
|
|
19.
Fu R J. Learning Semantic Hierarchies via Word Embeddings.
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics,2014:1199-1209
|
被引
4
次
|
|
|
|
|
20.
Yu Z. Learning Term Embeddings for Hypernymy Identification.
Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI 2015),2015:1390-1397
|
被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问