@article{
 title = {Selectional Preferences for Semantic Role Classification},
 type = {article},
 year = {2012},
 identifiers = {[object Object]},
 pages = {1-33},
 websites = {http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00145},
 publisher = {MIT Press 55 Hayward Street, Cambridge, MA 02142-1315 USA journals-info@mit.edu},
 id = {02a85d47-b5bf-306a-8ddb-1572066e70ac},
 created = {2013-08-08T06:59:15.000Z},
 file_attached = {false},
 profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
 group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
 last_modified = {2017-03-14T14:36:19.698Z},
 tags = {semantic role labeling},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Zapirain2012},
 private_publication = {false},
 abstract = {This paper focuses on a well-known open issue in Semantic Role Classification (SRC) research: the limited influence and sparseness of lexical features. We mitigate this problem using models that integrate automatically learned selectional preferences (SP). We explore a range of models based on WordNet and distributional-similarity SPs. Furthermore, we demonstrate that the SRC task is better modeled by SP models centered on both verbs and prepositions, rather than verbs alone. Our experiments with SP-based models in isolation indicate that they outperform a lexical baseline with 20 F1 points in domain and almost 40 F1 points out of domain. Furthermore, we show that a state-of-the-art SRC system extended with features based on selectional preferences performs significantly better, both in domain (17% error reduction) and out of domain (13% error reduction). Finally, we show that in an end-to-end semantic role labeling system we obtain small but statistically significant improvements, even though our modifie...},
 bibtype = {article},
 author = {Zapirain, Beñat and Agirre, Eneko and Màrquez, Lluís and Surdeanu, Mihai},
 journal = {Computational Linguistics}
}

{"_id":"SPP8C3A3bHy75ihE3","bibbaseid":"zapirain-agirre-mrquez-surdeanu-selectionalpreferencesforsemanticroleclassification-2012","authorIDs":[],"author_short":["Zapirain, B.","Agirre, E.","Màrquez, L.","Surdeanu, M."],"bibdata":{"title":"Selectional Preferences for Semantic Role Classification","type":"article","year":"2012","identifiers":"[object Object]","pages":"1-33","websites":"http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00145","publisher":"MIT Press 55 Hayward Street, Cambridge, MA 02142-1315 USA journals-info@mit.edu","id":"02a85d47-b5bf-306a-8ddb-1572066e70ac","created":"2013-08-08T06:59:15.000Z","file_attached":false,"profile_id":"5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6","group_id":"066b42c8-f712-3fc3-abb2-225c158d2704","last_modified":"2017-03-14T14:36:19.698Z","tags":"semantic role labeling","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Zapirain2012","private_publication":false,"abstract":"This paper focuses on a well-known open issue in Semantic Role Classification (SRC) research: the limited influence and sparseness of lexical features. We mitigate this problem using models that integrate automatically learned selectional preferences (SP). We explore a range of models based on WordNet and distributional-similarity SPs. Furthermore, we demonstrate that the SRC task is better modeled by SP models centered on both verbs and prepositions, rather than verbs alone. Our experiments with SP-based models in isolation indicate that they outperform a lexical baseline with 20 F1 points in domain and almost 40 F1 points out of domain. Furthermore, we show that a state-of-the-art SRC system extended with features based on selectional preferences performs significantly better, both in domain (17% error reduction) and out of domain (13% error reduction). Finally, we show that in an end-to-end semantic role labeling system we obtain small but statistically significant improvements, even though our modifie...","bibtype":"article","author":"Zapirain, Beñat and Agirre, Eneko and Màrquez, Lluís and Surdeanu, Mihai","journal":"Computational Linguistics","bibtex":"@article{\n title = {Selectional Preferences for Semantic Role Classification},\n type = {article},\n year = {2012},\n identifiers = {[object Object]},\n pages = {1-33},\n websites = {http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00145},\n publisher = {MIT Press 55 Hayward Street, Cambridge, MA 02142-1315 USA journals-info@mit.edu},\n id = {02a85d47-b5bf-306a-8ddb-1572066e70ac},\n created = {2013-08-08T06:59:15.000Z},\n file_attached = {false},\n profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},\n group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},\n last_modified = {2017-03-14T14:36:19.698Z},\n tags = {semantic role labeling},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Zapirain2012},\n private_publication = {false},\n abstract = {This paper focuses on a well-known open issue in Semantic Role Classification (SRC) research: the limited influence and sparseness of lexical features. We mitigate this problem using models that integrate automatically learned selectional preferences (SP). We explore a range of models based on WordNet and distributional-similarity SPs. Furthermore, we demonstrate that the SRC task is better modeled by SP models centered on both verbs and prepositions, rather than verbs alone. Our experiments with SP-based models in isolation indicate that they outperform a lexical baseline with 20 F1 points in domain and almost 40 F1 points out of domain. Furthermore, we show that a state-of-the-art SRC system extended with features based on selectional preferences performs significantly better, both in domain (17% error reduction) and out of domain (13% error reduction). Finally, we show that in an end-to-end semantic role labeling system we obtain small but statistically significant improvements, even though our modifie...},\n bibtype = {article},\n author = {Zapirain, Beñat and Agirre, Eneko and Màrquez, Lluís and Surdeanu, Mihai},\n journal = {Computational Linguistics}\n}","author_short":["Zapirain, B.","Agirre, E.","Màrquez, L.","Surdeanu, M."],"urls":{"Website":"http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00145"},"bibbaseid":"zapirain-agirre-mrquez-surdeanu-selectionalpreferencesforsemanticroleclassification-2012","role":"author","downloads":0,"html":""},"bibtype":"article","creationDate":"2020-02-06T23:48:12.232Z","downloads":0,"keywords":[],"search_terms":["selectional","preferences","semantic","role","classification","zapirain","agirre","màrquez","surdeanu"],"title":"Selectional Preferences for Semantic Role Classification","year":2012}