%0 Conference Paper %1 TagarevTolosiAlexiev2017-FD %A Tagarev, Andrey %A Tolosi, Laura %A Alexiev, Vladimir %B Semantic Keyword-based Search on Structured Data Sources %D 2016 %E Cardoso, Jorge %E Guerra, Francesco %E Houben, Geert-Jan %E Pinto, Alexandre Miguel %E Velegrakis, Yannis %I Springer %K Cultural_Heritage DBpedia Europeana Wikipedia categorization classification concept_extraction food_and_drink gazetteer semantic_enrichment %P 182-196 %R 10.1007/978-3-319-27932-9_16 %T Domain-specific modeling: Towards a Food and Drink Gazetteer %U http://link.springer.com/chapter/10.1007/978-3-319-27932-9_16 %V 9398 %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 a 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. In cases when the domain is not very specific (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. %& 16 %@ 978-3-319-27932-9

@inproceedings{TagarevTolosiAlexiev2017-FD, 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 a 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. In cases when the domain is not very specific (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/29029dbb76ec61a96568f9c7688f8c2bf/valexiev}, booktitle = {{Semantic Keyword-based Search on Structured Data Sources}}, chapter = 16, doi = {10.1007/978-3-319-27932-9_16}, editor = {Cardoso, Jorge and Guerra, Francesco and Houben, Geert-Jan and Pinto, Alexandre Miguel and Velegrakis, Yannis}, interhash = {edb544d970ab45885f7655a117744ca6}, intrahash = {9029dbb76ec61a96568f9c7688f8c2bf}, isbn = {978-3-319-27932-9}, keywords = {Cultural_Heritage DBpedia Europeana Wikipedia categorization classification concept_extraction food_and_drink gazetteer semantic_enrichment}, month = jan, note = {First COST Action IC1302 International KEYSTONE Conference (IKC 2015), Coimbra, Portugal, September 8-9, 2015. Revised Selected Papers}, pages = {182-196}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2021-08-25T16:07:36.000+0200}, title = {{Domain-specific modeling: Towards a Food and Drink Gazetteer}}, url = {http://link.springer.com/chapter/10.1007/978-3-319-27932-9_16}, url_preprint = {http://rawgit2.com/VladimirAlexiev/my/master/pubs/Tagarev2015-DomainSpecificGazetteer.pdf}, url_slides = {http://rawgit2.com/VladimirAlexiev/my/master/pubs/Tagarev2015-DomainSpecificGazetteer-slides.pdf}, volume = 9398, year = 2016 }