We describe a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity tags, semantic roles, semantically similar words and the likelihood that the sentence makes sense (grammatically and semantically) using a language model. The entire network is trained jointly on all these tasks in a end-to-end manner. All the tasks use labeled data except the language model which is learnt from unlabeled text and represents a novel form of semi-supervised learning for the shared tasks. We show how multitask learning, semi-supervised learning, as well as structured output learning improve the generalization of the shared tasks, resulting in state-of-the-art performance.

A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning (Ronan Collobert and Jason Weston, ICML 2008)