Natural Language Processing (Almost) from Scratch
Collobert et al., 2011, Natural Language Processing (Almost) from Scratch (Journal of Machine Learning Research)
Subscriber deck — free during early access
1 cards in “3. The Networks” · whole deck
3. The Networks
- What is the general structure of the networks in “NLP (Almost) from Scratch”?A first layer maps each word to a feature vector; a second layer extracts features from a window of words or the whole sentence (as a sequence, not a bag of words); then standard layers, trained end to end by backpropagation, output one score per tag.
- Collobert et al., 2011, Natural Language Processing (Almost) from Scratch (Journal of Machine Learning Research), 3. The Networks, pp. 2498–2499
Source
- Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu and Pavel Kuksa. 2011. Natural Language Processing (Almost) from Scratch. In Journal of Machine Learning Research, pp. 2493–2537. https://www.jmlr.org/papers/v12/collobert11a.html