Multilingual Modal Sense Classification using a Convolutional Neural Network [Source Code] (ICPSR doi:10.11588/data/ERDJDI)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

Document Description

Citation

Title:

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

Identification Number:

doi:10.11588/data/ERDJDI

Distributor:

heiDATA

Date of Distribution:

2019-10-07

Version:

1

Bibliographic Citation:

Marasović, Ana, 2019, "Multilingual Modal Sense Classification using a Convolutional Neural Network [Source Code]", https://doi.org/10.11588/data/ERDJDI, heiDATA, V1

Study Description

Citation

Title:

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

Identification Number:

doi:10.11588/data/ERDJDI

Authoring Entity:

Marasović, Ana (Department of Computational Linguistics, Heidelberg University, Germany)

Date of Production:

2016

Distributor:

heiDATA

Date of Distribution:

2019-10-07

Study Scope

Keywords:

Arts and Humanities, Computer and Information Science, Modal sense classification (MSC), Word Sense Disambiguation, modal verb, word embedding, semantic feature

Topic Classification:

semantic modeling

Abstract:

<p><strong>Abstract</strong></p> <p>Modal sense classification (MSC) is aspecial WSD task that depends on themeaning of the proposition in the modal&rsquo;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. </p> <p>(Marasović and Frank, 2016)</p>

Kind of Data:

program source code, python scripts

Methodology and Processing

Other Study-Related Materials

Label:

modal-sense-classifcation.zip

Notes:

application/zip