 Adding a CRF (Conditional Random Fields) layer as the final layer of recurrent network, then use a variant of the Viterbi algorithm to select the most likely tag sequence.

University of Michigan - Ann Arbor

- Choosing the maximum probability label for each element in a sequence independently does not necessarily result in an optimal (or even very good) sequence of tags.
- It doesn't guarantee the resulting sequence is well-formed or legal. For example, tag O might be followed by tag I; a tag I-LOC following a tag B-PER.

Drawbacks of IOB tagging

An on-going but a helpful book resource about NLP
https://web.stanford.edu/~jurafsky/slp3/

Learn Before

Related