Natural Language Processing (almost) from Scratch

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This versatility is achieved by trying to avoid task-specific engineering and therefore disregarding a lot of prior knowledge. Instead of exploiting man-made input features carefully optimized for each task, our system learns internal representations on the basis of vast amounts of mostly unlabeled training data. This work is then used as a basis for building a freely available tagging system with good performance and minimal computational requirements.

# Natural Language Processing Techniques # Computer Science # Topic Modeling # Speech and dialogue systems

Ronan Collobert, Jason Weston, Léon Bottou, et al. (2011). "Natural Language Processing (almost) from Scratch". arXiv (Cornell University). https://doi.org/10.48550/arxiv.1103.0398