Multilingual Modal Sense Classification using a Convolutional Neural Network
This work addresses modal sense classification for NLP researchers, but it is incremental as it applies an existing CNN method to a specific linguistic task.
The paper tackled modal sense classification in English and German using a CNN, showing it outperforms feature-based and standard NN classifiers, with analysis revealing known and new linguistic features and favorable performance on a standard WSD benchmark.
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.