The snapshot of a word means the most informative fragment of the word. By taking the snapshot instead of the whole, the value space of the lexical feature can be significantly r...
In recent years, the Natural Language Processing scene has witnessed the steady growth of interest in connectionist modeling. The main appeal of such an approach is that one does n...
This paper presents a semi-supervised training method for linear-chain conditional random fields that makes use of labeled features rather than labeled instances. This is accompli...
The present work advances the accuracy and training speed of discriminative parsing. Our discriminative parsing method has no generative component, yet surpasses a generative base...
We introduce one module in a cognitive system that learns the shape of objects by active exploration. More specifically, we propose a feature tracking scheme that makes use of the...
Nicolas Pugeault, Emre Baseski, Dirk Kraft, Floren...