OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

A neural network approach to selectional preference acquisition

Van de Cruys, Tim A neural network approach to selectional preference acquisition. (2014) In: Empirical Methods in Natural Language Processing (EMNLP), 25 October 2014 - 29 October 2014 (Doha, Qatar).

[img]
Preview
(Document in English)

PDF (Publisher's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
199kB

Official URL: https://doi.org/10.3115/v1/D14-1004

Abstract

This paper investigates the use of neural networks for the acquisition of selectional preferences. Inspired by recent advances of neural network models for NLP applications, we propose a neural network modelthat learns to discriminate between felicitous and infelicitous arguments for a particular predicate. The model is entirely unsupervised preferences are learned fromunannotated corpus data. We propose twoneural network architectures: one that handles standard two-way selectional prefer-ences and one that is able to deal with multi-way selectional preferences. Themodel’s performance is evaluated on a pseudo-disambiguation task, on which it is shown to achieve state of the art performance.

Item Type:Conference or Workshop Item (Paper)
Additional Information:Thanks to Association for Computational Linguistics. Thi is an open accees article available at the URL: https://www.aclweb.org/anthology/D14-1004
HAL Id:hal-02878928
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Laboratory name:
Statistics:download
Deposited On:16 Jun 2020 09:01

Repository Staff Only: item control page