Logo: Deutsches Institut für Internationale Pädagogische Forschung

Publications

Publikationendatenbank

show results

Autor:
Szarvas, György; Biemann, Chris; Gurevych, Iryna:

Titel:
Supervised all-words lexical substitution using delexicalized features

Quelle:
In: Association for Computational Linguistics (Hrsg.): Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT) Stroudsburg, Pa. : ACL (2013) , 1131-1141

URL des Volltextes:
https://www.ukp.tu-darmstadt.de/fileadmin/user_upload/Group_UKP/publikationen/2013/SzarvasBiemannGurevych_naaclhlt2013.pdf

Sprache:
Englisch

Dokumenttyp:
4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings

Schlagwörter:
Automatisierung, Computerlinguistik, Information Retrieval, Methode, Modell, Sinn, Synonym, Textanalyse, Thesaurus, Verfahren, Wort


Abstract(englisch):
We propose a supervised lexical substitution system that does not use separate classifiers per word and is therefore applicable to any word in the vocabulary. Instead of learning word-specific substitution patterns, a global model for lexical substitution is trained on delexicalized (i.e., non lexical) features, which allows to exploit the power of supervised methods while being able to generalize beyond target words in the training set. This way, our approach remains technically straightforward, provides better performance and similar coverage in comparison to unsupervised approaches. Using features from lexical resources, as well as a variety of features computed from large corpora (n-gram counts, distributional similarity) and a ranking method based on the posterior probabilities obtained from a Maximum Entropy classifier, we improve over the state of the art in the LexSub Best-Precision metric and the Generalized Average Precision measure. Robustness of our approach is demonstrated by evaluating it successfully on two different datasets.


DIPF-Abteilung:
Informationszentrum Bildung

Notizen:

last modified Nov 11, 2016