@inproceedings{daher2017cicling,
  author    = {Daher, Hani and Besan\c{c}on, Romaric and  Ferret, Olivier and  Le Borgne, Herv{\'e} and Daquo,Anne-Laure and  Tamaazousti, Youssef},
  title     = {Supervised Learning of Entity Disambiguation Models by Negative Sample Selection},
  booktitle = {18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing)},
  year      = {2017},
  address   = {Budapest, Hungary},
  note      = {17 -- 23 avril},
  doi       = {10.1007/978-3-319-77113-7_26},
  url_PDF   = {http://people.csail.mit.edu/ytamaaz/files/pdf/Supervised_Learning_of_Entity_Disambiguation_Models_by_Negative_Sample_Selection.pdf},
  abstract  = {The objective of Entity Linking is to connect an entity mention in a text to a known entity in a knowledge base. The general approach for this task is to generate, for a given mention, a set of candidate entities from the base and determine, in a second step, the best one. This paper focuses on this last step and proposes a method based on learning a function that discriminates an entity from its most ambiguous ones. Our contribution lies in the strategy to learn efficiently such a model while keeping it compatible with large knowledge bases. We propose three strategies with different efficiency/performance trade-off, that are experimentally validated on six datasets of the TAC evaluation campaigns by using Freebase and DBpedia as reference knowledge bases.},
  keywords  = {}
}

{"_id":"BDD7b5a2AJbMFE2on","bibbaseid":"daher-besanon-ferret-leborgne-daquo-tamaazousti-supervisedlearningofentitydisambiguationmodelsbynegativesampleselection-2017","author_short":["Daher, H.","Besançon, R.","Ferret, O.","Le Borgne, H.","Daquo, A.","Tamaazousti, Y."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Daher"],"firstnames":["Hani"],"suffixes":[]},{"propositions":[],"lastnames":["Besançon"],"firstnames":["Romaric"],"suffixes":[]},{"propositions":[],"lastnames":["Ferret"],"firstnames":["Olivier"],"suffixes":[]},{"propositions":[],"lastnames":["Le","Borgne"],"firstnames":["Hervé"],"suffixes":[]},{"propositions":[],"lastnames":["Daquo"],"firstnames":["Anne-Laure"],"suffixes":[]},{"propositions":[],"lastnames":["Tamaazousti"],"firstnames":["Youssef"],"suffixes":[]}],"title":"Supervised Learning of Entity Disambiguation Models by Negative Sample Selection","booktitle":"18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing)","year":"2017","address":"Budapest, Hungary","note":"17 – 23 avril","doi":"10.1007/978-3-319-77113-7_26","url_pdf":"http://people.csail.mit.edu/ytamaaz/files/pdf/Supervised_Learning_of_Entity_Disambiguation_Models_by_Negative_Sample_Selection.pdf","abstract":"The objective of Entity Linking is to connect an entity mention in a text to a known entity in a knowledge base. The general approach for this task is to generate, for a given mention, a set of candidate entities from the base and determine, in a second step, the best one. This paper focuses on this last step and proposes a method based on learning a function that discriminates an entity from its most ambiguous ones. Our contribution lies in the strategy to learn efficiently such a model while keeping it compatible with large knowledge bases. We propose three strategies with different efficiency/performance trade-off, that are experimentally validated on six datasets of the TAC evaluation campaigns by using Freebase and DBpedia as reference knowledge bases.","keywords":"","bibtex":"@inproceedings{daher2017cicling,\n author = {Daher, Hani and Besan\\c{c}on, Romaric and Ferret, Olivier and Le Borgne, Herv{\\'e} and Daquo,Anne-Laure and Tamaazousti, Youssef},\n title = {Supervised Learning of Entity Disambiguation Models by Negative Sample Selection},\n booktitle = {18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing)},\n year = {2017},\n address = {Budapest, Hungary},\n note = {17 -- 23 avril},\n doi = {10.1007/978-3-319-77113-7_26},\n url_PDF = {http://people.csail.mit.edu/ytamaaz/files/pdf/Supervised_Learning_of_Entity_Disambiguation_Models_by_Negative_Sample_Selection.pdf},\n abstract = {The objective of Entity Linking is to connect an entity mention in a text to a known entity in a knowledge base. The general approach for this task is to generate, for a given mention, a set of candidate entities from the base and determine, in a second step, the best one. This paper focuses on this last step and proposes a method based on learning a function that discriminates an entity from its most ambiguous ones. Our contribution lies in the strategy to learn efficiently such a model while keeping it compatible with large knowledge bases. We propose three strategies with different efficiency/performance trade-off, that are experimentally validated on six datasets of the TAC evaluation campaigns by using Freebase and DBpedia as reference knowledge bases.},\n keywords = {}\n}\n\n","author_short":["Daher, H.","Besançon, R.","Ferret, O.","Le Borgne, H.","Daquo, A.","Tamaazousti, Y."],"key":"daher2017cicling","id":"daher2017cicling","bibbaseid":"daher-besanon-ferret-leborgne-daquo-tamaazousti-supervisedlearningofentitydisambiguationmodelsbynegativesampleselection-2017","role":"author","urls":{" pdf":"http://people.csail.mit.edu/ytamaaz/files/pdf/Supervised_Learning_of_Entity_Disambiguation_Models_by_Negative_Sample_Selection.pdf"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://hleborgne.github.io/files/hleborgne-publications.bib","dataSources":["sJzmxoNKfHCgQoayi"],"keywords":[],"search_terms":["supervised","learning","entity","disambiguation","models","negative","sample","selection","daher","besançon","ferret","le borgne","daquo","tamaazousti"],"title":"Supervised Learning of Entity Disambiguation Models by Negative Sample Selection","year":2017}