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 “3.3.3 Tagging Schemes” · whole deck

3.3.3 Tagging Schemes

  1. Which tagging scheme did Collobert et al. use for segment tasks, and what are its tags?
    IOBES for all tasks, the most expressive: B-X begins a segment, I-X is inside, E-X ends it, S-X is a single-word segment, O is outside. For chunking, a one-word NP is S-NP; longer NPs are B-NP … I-NP … E-NP. Output was converted back to IOB for evaluation.

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