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

<p><strong>Abstract</strong></p>
<p>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. </p>
<p>(Marasović and Frank, 2016)</p>