Multilingual Modal Sense Classification using a Convolutional Neural Network

08/18/2016
by   Ana Marasović, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/21/2019

Unsupervised Learning of Neural Networks to Explain Neural Networks (extended abstract)

This paper presents an unsupervised method to learn a neural network, na...
research
05/24/2022

Highly Accurate FMRI ADHD Classification using time distributed multi modal 3D CNNs

This work proposes an algorithm for fMRI data analysis for the classific...
research
04/24/2015

Classifying Relations by Ranking with Convolutional Neural Networks

Relation classification is an important semantic processing task for whi...
research
11/10/2016

Landmark-based consonant voicing detection on multilingual corpora

This paper tests the hypothesis that distinctive feature classifiers anc...
research
11/27/2016

Semi Supervised Preposition-Sense Disambiguation using Multilingual Data

Prepositions are very common and very ambiguous, and understanding their...
research
07/04/2018

Towards Automation of Sense-type Identification of Verbs in OntoSenseNet(Telugu)

In this paper, we discuss the enrichment of a manually developed resourc...
research
06/15/2021

The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing

Modality is the linguistic ability to describe events with added informa...

Please sign up or login with your details

Forgot password? Click here to reset