TU Darmstadt / ULB / TUbiblio

Multilingual Modal Sense Classification using a Convolutional Neural Network

Marasovic, Ana and Frank, Anette (2016):
Multilingual Modal Sense Classification using a Convolutional Neural Network.
In: Proceedings of the 1st Workshop on Representation Learning, [Online-Edition: http://www.aclweb.org/anthology/W/W16/W16-1613.pdf],
[Conference or Workshop Item]

Abstract

Modal sense classification (MSC) is a special WSD task that depends on the meaning 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 benchmark the CNN on a standard WSD task, where it compares favorably to models using sense-disambiguated target vectors.

Item Type: Conference or Workshop Item
Erschienen: 2016
Creators: Marasovic, Ana and Frank, Anette
Title: Multilingual Modal Sense Classification using a Convolutional Neural Network
Language: German
Abstract:

Modal sense classification (MSC) is a special WSD task that depends on the meaning 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 benchmark the CNN on a standard WSD task, where it compares favorably to models using sense-disambiguated target vectors.

Title of Book: Proceedings of the 1st Workshop on Representation Learning
Uncontrolled Keywords: AIPHES_area_a3
Divisions: DFG-Graduiertenkollegs
DFG-Graduiertenkollegs > Research Training Group 1994 Adaptive Preparation of Information from Heterogeneous Sources
Date Deposited: 30 Dec 2016 17:45
Official URL: http://www.aclweb.org/anthology/W/W16/W16-1613.pdf
Identification Number: TUD-CS-2016-0143
Export:

Optionen (nur für Redakteure)

View Item View Item