Abstract
One of the most successful approaches to Word Sense Disambiguation (WSD) in the last decade has been the knowledge-based approach, which exploits lexical knowledge sources such as wordnets, ontologies, etc. The knowledge encoded in them is typically used as a sense inventory and as a relations bank. However, this type of information is rather sparse in terms of senses and the relations among them. In this paper we present a strategy for the enrichment of WSD knowledge bases with data-driven relations from a gold standard corpus (annotated with word senses, valency information, syntactic analyses, etc.). We focus on Bulgarian and English as use cases, but our approach is scalable to other languages as well. The results show that the addition of new knowledge improves accuracy on the WSD task in a statistically significant way.
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.
In this work we used version 3.0 of Princeton WordNet: https://wordnet.princeton.edu/.
- 5.
Available at http://compling.hss.ntu.edu.sg/omw/ .
- 6.
- 7.
- 8.
- 9.
- 10.
- 11.
Here we present the combination of synsets in each relation as POS. The POS are: A—adjective, N—noun, R—adverb, and V—verb. Also we present the number of arcs for the relations in WordNet.
- 12.
- 13.
Here we interpret the concept of “event'' in a wider sense that also includes states.
References
Agirre, E., Martinez, D.: Integrating selectional preferences in WordNet. In: Proceedings of First International WordNet Conference, Mysore, India. (2002)
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. Association for Computational Linguistics (2009)
Agirre, E., Lacalle, O.L., Soroa, A.: Random walks for knowledge-based word sense disambiguation. Comput. Linguist. 40(1), 57–84 (The Association for Computational Linguistics, MIT Press) (2014)
Brin, S., Page, L.: Reprint of: the anatomy of a large-scale hypertextual web search engine. Comput. Netw. 56(18), 3825–3833 (2012)
Fellbaum, C. (ed.): WordNet an Electronic Lexical Database. The MIT Press, Cambridge (1998)
Mihalcea, R., Moldovan, D.: Extended Wordnet: progress report. In: Proceedings of NAACL Workshop on WordNet and Other Lexical Resources, pp. 95–100 (2001)
Miller, G.A., Leacock, C., Tengi, R., Bunker, R.T.: A semantic concordance. In: Proceedings of HLT ‘93, pp. 303–308 (1993)
Montoyo, A., Suárez, A., Rigau, G., Palomar, M.: Combining knowledge-and corpus-based word-sense-disambiguation methods. J. Artif. Intell. Res. (JAIR) 23, 299–330 (2005)
Navigli, R., Ponzetto, S.P.: BabelNet: the automatic construction, evaluation and application of a wide-coverage multilingual semantic network. Artif. Intell. 193, 217–250 (Elsevier) (2012)
Osenova, P., Simov, K., Laskova, L., Kancheva, S.: A treebank-driven creation of an ontovalence verb lexicon for Bulgarian. In: Proceedings of the Eight International Conference on Language Resources and Evaluation, pp. 2636–2640 (2012)
Popov, A., Kancheva, S., Manova, S., Radev, I., Simov, K., Osenova, P.: The sense annotation of BulTreeBank. In: Proceedings of the Thirteenth International Workshop on Treebanks and Linguistic Theories, pp. 127–136 (2014)
Acknowledgments
This research has received partial support by the EC’s FP7 (FP7/2007–2013) project under grant agreement number 610516: “QTLeap: Quality Translation by Deep Language Engineering Approaches” and FP7 grant 316087 AComIn “Advanced Computing for Innovation”, funded by the European Commission in 20122016. The AComIN project kindly supported the scientific visits of Kiril Simov and Petya Osenova in Amsterdam, at Vrije Universiteit in 2014 and 2015. The authors would like to thank prof. Piek Vossen for hosting these visits as well as for the fruitful discussions in his group.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Simov, K., Popov, A., Osenova, P. (2016). Knowledge Graph Extension for Word Sense Annotation. In: Margenov, S., Angelova, G., Agre, G. (eds) Innovative Approaches and Solutions in Advanced Intelligent Systems . Studies in Computational Intelligence, vol 648. Springer, Cham. https://doi.org/10.1007/978-3-319-32207-0_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-32207-0_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-32206-3
Online ISBN: 978-3-319-32207-0
eBook Packages: EngineeringEngineering (R0)