Multilingual Modal Sense Classification using a Convolutional Neural Network [Source Code]

DOI

Abstract Modal sense classification (MSC) is aspecial WSD task that depends on themeaning of the proposition in the modal’s scope. We explore a CNN architecture for classifying modal sense in English and German. We show that CNNs are superior to manually designed feature-based classifiers and a standard NN classifier. We analyze the feature maps learned by the CNN and identify known and previously unattested linguistic features. We bench-mark the CNN on a standard WSD task,where it compares favorably to models using sense-disambiguated target vectors. (Marasović and Frank, 2016)

Identifier
DOI https://doi.org/10.11588/data/ERDJDI
Related Identifier https://doi.org/10.18653/v1/W16-1613
Metadata Access https://heidata.uni-heidelberg.de/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=doi:10.11588/data/ERDJDI
Provenance
Creator Marasović, Ana (Department of Computational Linguistics, Heidelberg University, Germany)
Publisher heiDATA
Contributor Marasović, Ana
Publication Year 2019
Rights Licensed under <a href="https://www.gnu.org/licenses/gpl-3.0.en.html">General Public License v3 (GPL v3)</a>.; info:eu-repo/semantics/openAccess
OpenAccess true
Contact Marasović, Ana (Department of Computational Linguistics, Heidelberg University, Germany)
Representation
Resource Type program source code, python scripts; Dataset
Format application/zip
Size 3094680
Version 1.0
Discipline Humanities
Spatial Coverage Heidelberg University