• DOI:10.1145/1390156.1390177
Corpus ID: 2617020

A unified architecture for natural language processing: deep neural networks with multitask learning

@inproceedings{Collobert2008AUA,
  title={A unified architecture for natural language processing: deep neural networks with multitask learning},
  author={Ronan Collobert and J. Weston},
  booktitle={ICML '08},
  year={2008}
}

• Ronan Collobert, J. Weston
• Published in ICML '08 2008
• Computer Science

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 using weight-sharing, an instance of multitask learning. All the tasks use labeled data except the language… Expand

View on ACM

icml2008.cs.helsinki.fi

Save to Library

Create Alert

Cite

Launch Research Feed