Multilingual Modal Sense Classification using a Convolutional Neural Network

TL;DR

This paper presents a CNN-based approach for multilingual modal sense classification, demonstrating its superiority over traditional classifiers and analyzing learned linguistic features in English and German.

Contribution

It introduces a CNN architecture for MSC in multiple languages and provides a detailed analysis of the features learned by the model.

Findings

CNN outperforms feature-based and standard neural classifiers

The model identifies known and new linguistic features

Benchmark results favor CNN over sense-disambiguated vector models

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.