%0 Conference Paper %1 TagarevTolosiAlexiev2017-FD-extended %A Tagarev, Andrey %A Tolosi, Laura %A Alexiev, Vladimir %B Transactions on Computational Collective Intelligence XXVI, special issue on Keyword Search in Big Data %D 2017 %E Nguyen, Ngoc Thanh %E Kowalczyk, Ryszard %E Pinto, Alexandre Miguel %E Cardoso, Jorge %I Springer %K Cultural_Heritage DBpedia Europeana Wikipedia categorization classification concept_extraction food_and_drink gazetteer semantic_enrichment %P 186-209 %R 10.1007/978-3-319-59268-8_9 %T Domain-specific modeling: a Food and Drink Gazetteer %V 10190 %X Our goal is to build a Food and Drink (FD) gazetteer that can serve for classification of general, FD-related concepts, efficient faceted search or automated semantic enrichment. Fully supervised design of domain-specific models ex novo is not scalable. Integration of several ready knowledge bases is tedious and does not ensure coverage. Completely data-driven approaches require a large amount of training data, which is not always available. For general domains (such as the FD domain), re-using encyclopedic knowledge bases like Wikipedia may be a good idea. We propose here a semi-supervised approach that uses a restricted Wikipedia as a base for the modeling, achieved by selecting a domain-relevant Wikipedia category as root for the model and all its subcategories, combined with expert and data-driven pruning of irrelevant categories.

@inproceedings{TagarevTolosiAlexiev2017-FD-extended, abstract = {Our goal is to build a Food and Drink (FD) gazetteer that can serve for classification of general, FD-related concepts, efficient faceted search or automated semantic enrichment. Fully supervised design of domain-specific models ex novo is not scalable. Integration of several ready knowledge bases is tedious and does not ensure coverage. Completely data-driven approaches require a large amount of training data, which is not always available. For general domains (such as the FD domain), re-using encyclopedic knowledge bases like Wikipedia may be a good idea. We propose here a semi-supervised approach that uses a restricted Wikipedia as a base for the modeling, achieved by selecting a domain-relevant Wikipedia category as root for the model and all its subcategories, combined with expert and data-driven pruning of irrelevant categories.}, added-at = {2021-08-25T16:07:36.000+0200}, author = {Tagarev, Andrey and Tolosi, Laura and Alexiev, Vladimir}, biburl = {https://www.bibsonomy.org/bibtex/22c6f11ab9051c00cef8a01692c8d5004/valexiev}, booktitle = {Transactions on Computational Collective Intelligence XXVI, special issue on Keyword Search in Big Data}, doi = {10.1007/978-3-319-59268-8_9}, editor = {Nguyen, Ngoc Thanh and Kowalczyk, Ryszard and Pinto, Alexandre Miguel and Cardoso, Jorge}, interhash = {f8dc8fcc5042a9240ed54fbfd20deb91}, intrahash = {2c6f11ab9051c00cef8a01692c8d5004}, keywords = {Cultural_Heritage DBpedia Europeana Wikipedia categorization classification concept_extraction food_and_drink gazetteer semantic_enrichment}, month = jul, pages = {186-209}, publisher = {Springer}, series = {LNCS}, timestamp = {2021-08-25T16:07:36.000+0200}, title = {{Domain-specific modeling: a Food and Drink Gazetteer}}, url_preprint = {http://rawgit2.com/VladimirAlexiev/my/master/pubs/Tagarev2017-DomainSpecificGazetteer.pdf}, url_published = {https://link.springer.com/chapter/10.1007/978-3-319-59268-8_9}, volume = 10190, year = 2017 }