Abstract
The paper focuses on the manipulation of a WordNet-based knowledge graph by adding, changing and combining various semantic relations. This is done in the context of measuring similarity and relatedness between words, based on word embedding representations trained on a pseudo corpus generated from the knowledge graph. The UKB tool is used for generating pseudo corpora that are then used for learning word embeddings. The results from the performed experiments show that the addition of more relations generally improves performance along both dimensions – similarity and relatedness. In line with previous research, our survey confirms that paradigmatic relations predominantly improve similarity, while syntagmatic relations benefit relatedness scores.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
- 4.
Downloaded from http://alfonseca.org/eng/research/wordsim353.html.
- 5.
Downloaded from https://www.cl.cam.ac.uk/~fh295/simlex.html.
- 6.
- 7.
The models are downloaded from here https://github.com/3Top/word2vec-api.
- 8.
References
Agirre, E., López de Lacalle, O., Soroa, A.: Random walks for knowledge-based word sense disambiguation. Comput. Linguist. 40(1), 57–84 (2014). http://dx.doi.org/10.1162/COLI_a_00164
Agirre, E., Soroa, A.: Personalizing PageRank for word sense disambiguation. In: Proceedings of the 12th Conference of the European Chapter of the ACL, EACL 2009, pp. 33–41 (2009). http://www.aclweb.org/anthology/E09-1005
Fellbaum, C. (ed.): WordNet An Electronic Lexical Database. The MIT Press, Cambridge (1998). http://mitpress.mit.edu/catalog/item/default.asp?ttype=2&tid=8106
Goikoetxea, J., Agirre, E., Soroa, A.: Single or multiple? Combining word representations independently learned from text and WordNet. In: AAAI, pp. 2608–2614. AAAI Press (2016)
Goikoetxea, J., Soroa, A., Agirre, E.: Random walks and neural network language models on knowledge bases. In: HLT-NAACL, The Association for Computational Linguistics, pp. 1434–1439 (2015)
Hill, F., Reichart, R., Korhonen, A.: Simlex-999: evaluating semantic models with (genuine) similarity estimation. In: Computational Linguistics (2015)
Hirst, G., St-Onge, D.: Lexical chains as representations of context for the detection and correction of malapropisms. In: Fellbaum, C. (ed.) WordNet: An Electronic Lexical Database, pp. 305–332. MIT Press, Cambridge (1998)
Iacobacci, I., Pilehvar, M.T., Navigli, R.: Sensembed: learning sense embeddings for word and relational similarity. In: ACL, vol. 1, pp. 95–105 (2015)
Mihalcea, R., Moldovan, D.I.: Extended WordNet: progress report. In: Proceedings of NAACL Workshop on WordNet and Other Lexical Resources, pp. 95–100 (2001)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. CoRR abs/1301.3781 (2013). http://arxiv.org/abs/1301.3781
Miller, G.A., Leacock, C., Tengi, R., Bunker, R.T.: A semantic concordance. In: Proceedings of HLT 1993, pp. 303–308 (1993). http://dx.doi.org/10.3115/1075671.1075742
Ponzetto, S.P., Navigli, R.: Knowledge-rich word sense disambiguation rivaling supervised systems. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010, Association for Computational Linguistics, Stroudsburg, PA, USA, pp. 1522–1531 (2010). http://dl.acm.org/citation.cfm?id=1858681.1858835
Ristoski, P., Paulheim, H.: RDF2Vec: RDF Graph Embeddings for Data Mining. Springer, Cham (2016). http://dx.doi.org/10.1007/978-3-319-46523-4_30
Salahli, M.A.: An approach for measuring semantic relatedness between words via related terms. Math. Comput. Appl. 14(1), 55–63 (2009). http://www.mcajournal.org/volume14/Vol14No1p.55.pdf
Simov, K., Osenova, P., Popov, A.: Using Context Information for Knowledge-Based Word Sense Disambiguation. Springer, Cham (2016). http://dx.doi.org/10.1007/978-3-319-44748-3_13
Simov, K., Popov, A., Osenova, P.: Improving word sense disambiguation with linguistic knowledge from a sense annotated treebank. Proc. RANLP 2015, 596–603 (2015)
Simov, K., Popov, A., Osenova, P.: The role of the WordNet relations in the knowledge-based word sense disambiguation task. In: Proceedings of Eighth Global WordNet Conference, pp. 391–398 (2016)
Acknowledgements
This research has received partial support by the grant 02/12—Deep Models of Semantic Knowledge (DemoSem), funded by the Bulgarian National Science Fund in 2017–2019. We are grateful to the anonymous reviewers for their remarks, comments, and suggestions. All errors remain our own responsibility.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Simov, K., Osenova, P., Popov, A. (2017). Comparison of Word Embeddings from Different Knowledge Graphs. In: Gracia, J., Bond, F., McCrae, J., Buitelaar, P., Chiarcos, C., Hellmann, S. (eds) Language, Data, and Knowledge. LDK 2017. Lecture Notes in Computer Science(), vol 10318. Springer, Cham. https://doi.org/10.1007/978-3-319-59888-8_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-59888-8_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59887-1
Online ISBN: 978-3-319-59888-8
eBook Packages: Computer ScienceComputer Science (R0)