Scholarly record
METHOD AND APPARATUS FOR AUTOMATED LINGUISTIC ONTOLOGY EXTENSION BY USING GOOGLE NGRAMS
Abstract
Extracting information from a text is an undivided part of modern NLP applications. Ontologies and semantic networks play important role in sense disambiguation problem, helping us distinguish concept nodes in text inputs. As we know, every language is always changing. Each generation of people adds something new to it, and new terms and word forms emerge while others become deprecated and people stop using them. Therefore modern linguistic ontologies have to store this information within a concept node. In this paper the brief overview for the state of the art in the sphere of temporal databases is presented. Authors nowadays tend to implement temporal knowledge bases for their purposes and successfully use it. There are several remarkable examples of production ready systems with temporal properties provided. In this paper it is suggested to implement temporal properties for the ontology, developed by the authors in previous works. At least, each concept or term in the ontology should contain the information about the start and the end of its existence. Google Ngram Viewer was used to provide information about concepts or terms frequencies by year based on a text corpus which includes many books (even in Russian) from the year 1500 to nowadays. A new method and apparatus for automated linguistic ontology extension is proposed. A proof of concept was implemented during this work and the existing ontology was expanded with temporal fields by using Google Ngrams. The next step will be fulfilling all missed dates in our database by means of this approach.
Publication Impact Profile
- Captures
- Mendeley - Readers: 1
Publication details
References10
Klimenkov S., Tsopa E., Pismak A., Yarkeev A., Reconstruction of Implied Semantic Relations in Russian Wiktionary, KEOD, 2016, pp. 74-80;
Hazman M., El-Beltagy S. R., Rafea A., A survey of ontology learning approaches, International Journal of Computer Applications, 22(9), 2011, pp. 36-43;
Buerli, M., 2012, The Current State of Graph Databases, Department of Computer Science, Cal Poly San Luis Obispo, California, 2012, pp 67-83;
Baratis E., Petrakis E. G., Batsakis S., Maris N., Papadakis N., TOQL: Temporal ontology querying language, International Symposium on Spatial and Temporal Databases, Springer, Berlin, Heidelberg, 2009, pp. 338-354;
Preventis A., Petrakis E. G., Batsakis S., Chronos Ed: A tool for handling temporal ontologies in Protege, International Journal on Artificial Intelligence Tools, 23(04), 2014, 1460018;
de Cesare S., Foy G., Partridge C., Re-engineering data with 4D ontologies and graph databases, International Conference on Advanced Information Systems Engineering, Springer, Berlin, Heidelberg, 2013, pp. 304-316;
Frank A. U., Ontology for spatio-temporal databases, Spatio-temporal databases, Springer, Berlin, Heidelberg, 2003, pp. 9-77;
George B., Shekhar S., Time-aggregated graphs for modeling spatio-temporal networks, Journal on Data Semantics XI, Springer, Berlin, Heidelberg, 2008, pp. 191-212;
Campos A., Mozzino J., Vaisman A., Towards temporal graph databases, Alberto Mendelzon Workshop on foundations of data management, 2016;
Grandi F., Multi-temporal RDF Ontology Versioning, Proceedings of the 3rd International Workshop on Ontology Dynamics (IWOD-09), Chantilly, VA, USA, 2009.
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.