Abstract
Recognising entities in a text and linking them to an external resource is a vital step in creating a structured resource (e.g. a knowledge base) from text. This allows semantic querying over a dataset, for example selecting all politicians or football players. However, traditional named entity recognition systems only distinguish a limited number of entity types (such as Person, Organisation and Location) and entity linking has the limitation that often not all entities found in a text can be linked to a knowledge base. This creates a gap in coverage between what is in the text and what can be annotated with fine grained types.
This paper presents an approach to detect entity types using DBpedia type information and distributional semantics. The distributional semantics paradigm assumes that similar words occur in similar contexts. We exploit this by comparing entities with an unknown type to entities for which the type is known and assign the type of the most similar set of entities to the entity with the unknown type. We demonstrate our approach on seven different named entity linking datasets.
To the best of our knowledge, our approach is the first to combine word embeddings with external type information for this task. Our results show that this task is challenging but not impossible and performance improves when narrowing the search space by adding more context to the entities in the form of topic information.
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
Similar content being viewed by others
Notes
- 1.
As entities are made up of words, we hypothesise that this also extends to entities.
- 2.
- 3.
For this paper, we ran experiments on a Ubuntu machine with 2 CPUs, 16 GB of RAM and most experiments did not take longer than 2 h.
- 4.
AIDA-YAGO2 originally contained Wikipedia URLs but these have been mapped to their corresponding DBpedia URIs.
- 5.
- 6.
Available from: http://www.jmlr.org/papers/volume5/lewis04a/lyrl2004_rcv1v2_ README.htm Last visited: 27 April 2016.
- 7.
- 8.
- 9.
- 10.
- 11.
- 12.
- 13.
- 14.
- 15.
- 16.
- 17.
Unfortunately, no further information about the Google News corpus is available as it is not an open dataset.
- 18.
- 19.
- 20.
References
ACE (Automatic Content Extraction) english annotation guidelines for entities (2006). http://www.ldc.upenn.edu/Projects/ACE/
Bengio, Y., Ducharme, R., Vincent, P., Jauvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 1137–1155 (2003)
Cano, A.E., Rizzo, G., Varga, A., Rowe, M., Stankovic, M., Dadzie, A.S.: Making sense of microposts (#Microposts2014) named entity extraction & linking challenge. In: 4th International Workshop on Making Sense of Microposts. #Microposts (2014)
Elsner, M., Charniak, E., Johnson, M.: Structured generative models for unsupervised named-entity clustering. In: Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2009), pp. 164–172 (2009)
van Erp, M., Ilievski, F., Rospocher, M., Vossen, P.: Missing Mr. Brown and buying an Abraham Lincoln - dark entities and DBpedia. In: Proceedings of NLP & DBpedia 2015 Workshop in Conjunction with 14th International Semantic Web Conference (ISWC 2015). CEUR Workshop Proceedings (2015)
van Erp, M., Mendes, P., Paulheim, H., Ilievski, F., Plu, J., Rizzo, G., Waitelonis, J.: Evaluating entity linking: an analysis of current benchmark datasets and a roadmap for doing a better job. In: Proceedings of LREC 2016 (2016). Preprint available from: https://mariekevanerp.files.wordpress.com/2012/06/evaluating-entity-linking-1.pdf
Grishman, R., Sundheim, B.M.: Message understanding conference - 6: a brief history. In: Proceedings International Conference on Computational Linguistics (1996)
Hachey, B., Radford, W., Nothman, J., Honnibal, M., Curran, J.R.: Evaluating entity linking with Wikipedia. Artif. Intell. 9, 130–150 (2013)
Hoffart, J., Yosef, M.A., Bordin, I., Fürstenau, H., Pinkal, M., Spaniol, M., Taneva, B., Thater, S., Weikum, G.: Robust disambiguation of named entities. In: Conference on Empirical Methods in Natural Language Processing. EMNLP (2011)
Kittur, A., Chi, E.H., Suh, B.: What’s in Wikipedia?: mapping topics and conflict using socially annotated category structure. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI 2009), pp. 1509–1512. ACM, New York (2009)
Lewis, D.D., Yang, Y., Rose, T.G., Li, F.: RCV1: a new benchmark collection for text categorization research. J. Mach. Learn. Res. 5, 361–397 (2004)
Mendes, P.N., Jakob, M., García-Silva, A., Bizer, C.: Dbpedia spotlight: shedding light on the web of documents. In: Proceedings of the 7th International Conference on Semantic Systems (I-SEMANTICS 2011), Graz, Austria. ACM New York, 7–9 September 2011
Mihalcea, R., Csomai, A.: Wikify! linking document to encyclopedic knowledge. In: Proceedings of the Sixteenth ACM Conference on Information and Knowledge Management (CIKM 2007), pp. 233–242 (2007)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: arXiv preprint arXiv:1301.3781 (2013)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Proceedings of NIPS (2013)
Milne, D., Witten, I.H.: Learning to link with Wikipedia. In: Proceedings of the 17th ACM Conference on Information and Knowledge Management (CIKM 2008), pp. 509–518 (2008)
Minard, A.L., Speranza, M., Urizar, R., na Altuna, B., van Erp, M., Schoen, A., van Son, C.: MEANTIME, the newsreader multilingual event and time corpus. In: Proceedings of the 10th Edition of the Language Resources and Evaluation Conference (LREC 2016) (2016)
Nadeau, D.: Semi-supervised named entity recognition: learning to recognize 100 entity types with little supervision. Ph.D. thesis, University of Ottawa (2007)
Nguyen, T.H., Grishman, R.: Relation extraction: perspective from convolutional neural networks. In: Proceedings of NAACL-HLT 2015, Denver, Colorado, USA, pp. 39–48, 31 May – 5 June 2015
Nuzzolese, A.G., Gentile, A.L., Presutti, V., Gangemi, A., Garigliotti, D., Navigli, R.: Open knowledge extraction challenge. In: Gandon, F., Cabrio, E., Stankovic, M., Zimmermann, A. (eds.) SemWebEval 2015. CCIS, vol. 548, pp. 3–15. Springer, Cham (2015). doi:10.1007/978-3-319-25518-7_1
Rizzo, G., Cano Amparo, E., Pereira, B., Varga, A.: Making sense of microposts (#Microposts2015) named entity recognition & linking challenge. In: 5th International Workshop on Making Sense of Microposts. #Microposts (2015)
Rizzo, G., Troncy, R.: NERD: a framework for unifying named entity recognition and disambiguation extraction tools. In: 13th Conference of the European Chapter of the Association for computational Linguistics (EACL 2012) (2012)
Röder, M., Usbeck, R., Hellmann, S., Gerber, D., Both, A.: N3-a collection of datasets for named entity recognition and disambiguation in the NLP interchange format. In: 9th Language Resources and Evaluation Conference. LREC (2014)
Sang, E.F.T.K.: Introduction to the CoNLL-2002 shared task: language-independent named entity recognition. In: Proceedings of CoNLL-2002, Taipei, Taiwan (2002)
Sekine, S., Sudo, K., Nobata, C.: Extended named entity hierarchy. In: Proceedings of the Third International Conference on Language Resources and Evaluation, pp. 1818–1824 (2002)
Sienčnik, S.K.: Adapting word2vec to named entity recognition. In: Proceedings of the 20th Nordic Conference of Computational Linguistics (NODALIDA 2015), Vilnius, Lithuania, pp. 239–243, 11–13 May 2015
Tjong Kim Sang, E.F., De Meulder, F.: Introduction to the CoNLL-2003 shared task: language-independent named entity recognition. In: Conference on Computational Natural Language Learning. CoNLL (2003)
Usbeck, R., Ngomo, A.C.N., Röder, M., Gerber, D., Coelho, S.A., Auer, S., Both, A.: AGDISTIS -graph-based disambiguation of named entities using linked data. In: Proceedings of the 13th International Semantic Web Conference (ISWC 2014), Riva del Garda, Italy, pp. 457–471, October 2014
Waitelonis, J., Exeler, C., Sack, H.: Linked data enabled generalized vector space model to improve document retrieval. In: Proceedings of NLP & DBpedia 2015 Workshop in Conjunction with 14th International Semantic Web Conference (ISWC2015). CEUR Workshop Proceedings (2015)
Acknowledgements
The research for this paper was made possible by the CLARIAH-CORE project financed by NWO: http://www.clariah.nl.
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
van Erp, M., Vossen, P. (2017). Entity Typing Using Distributional Semantics and DBpedia. In: van Erp, M., et al. Knowledge Graphs and Language Technology. ISWC 2016. Lecture Notes in Computer Science(), vol 10579. Springer, Cham. https://doi.org/10.1007/978-3-319-68723-0_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-68723-0_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68722-3
Online ISBN: 978-3-319-68723-0
eBook Packages: Computer ScienceComputer Science (R0)