A PRIORY INFORMATION AS WAY OF ONTOLOGICAL AND LANGUAGE HOMONYMY DISAMBIGUATION
Antonov Egor Sergeevich
Moscow State University named after M. V. Lomonosov
Abstract. The author considers the reasonability of a priory information use for the disambiguation of the language and ontological homonymy of named entities, by the material of marked corpus from 1700 English-language news articles verifies the strategy of choosing the most probable object with two adaptable parameters (the minimum probability of compliance, the minimum number of references in the corpus), and concludes that such a strategy allows achieving the high accuracy of homonymy disambiguation, but its use does not make sense for a large number of ontology objects because of low completeness.
Key words and phrases: распознавание именованных сущностей, разрешение омонимии именованных сущностей, онтология, априорная информация, географические объекты, новостные тексты, named entities recognition, disambiguation of named entities homonymy, ontology, a priory information, geographic objects, news texts
Open the whole article in PDF format. Free PDF-files viewer can be downloaded .
References:
Antonov E. S. Kak naiti million // RSDN Magazine. SPb.: K-Press, 2011. № 1. S. 60-68.
Cucerzan S. Large Scale Named Entity Disambiguation Based on Wikipedia Data // Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Stroudsburg, PA: Association for Computational Linguistics, 2007. P. 708-716.
Fader A., Soderland S., Etzioni O. Scaling Wikipedia-Based Named Entity Disambiguation to Arbitrary Web Text // Proceedings of the WikiAI 09 - IJCAI Workshop: User Contributed Knowledge and Artificial Intelligence: an Evolving Synergy. Pasadena, CA: IJCAI Organization, 2009. P. 21-28.
Hoffart J., Yosef M. A., Bordino I., Furstenau H., Pinkal M., Spaniol M., Taneva B., Thater S., Weikum G. Robust Disambiguation of Named Entities in Text // Proceedings of Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2011. P. 782-792.
Русский
