A flexible, corpus-driven model of regular and inverse selectional preferences
We present a vector space-based model for selectional preferences that predicts plausibility scores for argument headwords. It does not require any lexical resources (such as WordNet). It can be trained either on one corpus with syntactic annotation, or on a combination of a small semantically annot...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
December 01, 2010
|
| In: |
Computational linguistics
Year: 2010, Jahrgang: 36, Heft: 4, Pages: 723-763 |
| ISSN: | 1530-9312 |
| DOI: | 10.1162/coli_a_00017 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1162/coli_a_00017
|
| Verfasserangaben: | Katrin Erk, Sebastian Padó, Ulrike Padó |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 184012539X | ||
| 003 | DE-627 | ||
| 005 | 20230710145047.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230327s2010 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1162/coli_a_00017 |2 doi | |
| 035 | |a (DE-627)184012539X | ||
| 035 | |a (DE-599)KXP184012539X | ||
| 035 | |a (OCoLC)1389807098 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 28 |2 sdnb | ||
| 100 | 1 | |a Erk, Katrin |e VerfasserIn |0 (DE-588)136003753 |0 (DE-627)573860319 |0 (DE-576)300772580 |4 aut | |
| 245 | 1 | 2 | |a A flexible, corpus-driven model of regular and inverse selectional preferences |c Katrin Erk, Sebastian Padó, Ulrike Padó |
| 264 | 1 | |c December 01, 2010 | |
| 300 | |a 41 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 27.03.2023 | ||
| 520 | |a We present a vector space-based model for selectional preferences that predicts plausibility scores for argument headwords. It does not require any lexical resources (such as WordNet). It can be trained either on one corpus with syntactic annotation, or on a combination of a small semantically annotated primary corpus and a large, syntactically analyzed generalization corpus. Our model is able to predict inverse selectional preferences, that is, plausibility scores for predicates given argument heads.We evaluate our model on one NLP task (pseudo-disambiguation) and one cognitive task (prediction of human plausibility judgments), gauging the influence of different parameters and comparing our model against other model classes. We obtain consistent benefits from using the disambiguation and semantic role information provided by a semantically tagged primary corpus. As for parameters, we identify settings that yield good performance across a range of experimental conditions. However, frequency remains a major influence of prediction quality, and we also identify more robust parameter settings suitable for applications with many infrequent items. | ||
| 700 | 1 | |a Padó, Sebastian |d 1978- |e VerfasserIn |0 (DE-588)1033924393 |0 (DE-627)743676017 |0 (DE-576)381606112 |4 aut | |
| 700 | 1 | |a Padó, Ulrike |d 1980- |e VerfasserIn |0 (DE-588)13305280X |0 (DE-627)537494901 |0 (DE-576)26555621X |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Computational linguistics |d Cambridge, MA : MIT Press, 1980 |g 36(2010), 4 vom: Dez., Seite 723-763 |h Online-Ressource |w (DE-627)320641066 |w (DE-600)2025069-1 |w (DE-576)091205964 |x 1530-9312 |7 nnas |a A flexible, corpus-driven model of regular and inverse selectional preferences |
| 773 | 1 | 8 | |g volume:36 |g year:2010 |g number:4 |g month:12 |g pages:723-763 |g extent:41 |a A flexible, corpus-driven model of regular and inverse selectional preferences |
| 856 | 4 | 0 | |u https://doi.org/10.1162/coli_a_00017 |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20230327 | ||
| 993 | |a Article | ||
| 994 | |a 2010 | ||
| 998 | |g 1033924393 |a Padó, Sebastian |m 1033924393:Padó, Sebastian |d 90000 |d 90500 |e 90000PP1033924393 |e 90500PP1033924393 |k 0/90000/ |k 1/90000/90500/ |p 2 | ||
| 999 | |a KXP-PPN184012539X |e 4297367890 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"title":[{"title":"A flexible, corpus-driven model of regular and inverse selectional preferences","title_sort":"flexible, corpus-driven model of regular and inverse selectional preferences"}],"person":[{"role":"aut","roleDisplay":"VerfasserIn","display":"Erk, Katrin","given":"Katrin","family":"Erk"},{"family":"Padó","given":"Sebastian","roleDisplay":"VerfasserIn","display":"Padó, Sebastian","role":"aut"},{"family":"Padó","given":"Ulrike","display":"Padó, Ulrike","roleDisplay":"VerfasserIn","role":"aut"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"note":["Gesehen am 27.03.2023"],"language":["eng"],"recId":"184012539X","origin":[{"dateIssuedDisp":"December 01, 2010","dateIssuedKey":"2010"}],"id":{"eki":["184012539X"],"doi":["10.1162/coli_a_00017"]},"name":{"displayForm":["Katrin Erk, Sebastian Padó, Ulrike Padó"]},"physDesc":[{"extent":"41 S."}],"relHost":[{"title":[{"title":"Computational linguistics","title_sort":"Computational linguistics"}],"language":["eng"],"corporate":[{"display":"Association for Computational Linguistics","roleDisplay":"Herausgebendes Organ","role":"isb"}],"recId":"320641066","disp":"A flexible, corpus-driven model of regular and inverse selectional preferencesComputational linguistics","note":["Gesehen am 26.10.2020"],"type":{"bibl":"periodical","media":"Online-Ressource"},"part":{"pages":"723-763","issue":"4","year":"2010","extent":"41","text":"36(2010), 4 vom: Dez., Seite 723-763","volume":"36"},"pubHistory":["6.1980 -"],"name":{"displayForm":["Association for Computational Linguistics"]},"id":{"issn":["1530-9312"],"eki":["320641066"],"zdb":["2025069-1"]},"origin":[{"publisherPlace":"Cambridge, MA","dateIssuedDisp":"1980-","dateIssuedKey":"1980","publisher":"MIT Press"}],"physDesc":[{"extent":"Online-Ressource"}]}]} | ||
| SRT | |a ERKKATRINPFLEXIBLECO0120 | ||