 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.

A solution to the bad-formed sequence in IOB tagging

- 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.

University of Michigan - Ann Arbor

Named entity recognition is to find and classify spans of text that correspond to names of people, places or organizations. To use sequence labeling for a span-recognition problem, we’ll use a technique called IOB encoding.

Sequence labeling: named entity recognition

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

Speech and Language Processing (3rd ed. draft) 

For one class of entity, we label any token that begins a span of named entity with the label B, tokens that occur inside a span are tagged with an I, and any tokens outside of any span of interest are labeled O.

IOB encoding (single entity)

Drawbacks of IOB tagging

Many NLP systems make use of NER systems:
- Search engine efficiency
- Recommendation engine
- Customer service (assigning proper agent)
- Automatic trading

Applications of Named Entity Recognition (NER) 

The standard IOB (Inside, Outside, Beginning) tagging scheme uses the tag set $${\mathrm{B}, \mathrm{I}, \mathrm{O}}$$ to identify entities. When extending this to multiple entity types, the 'B' and 'I' tags are specialized for each class. For example, $$\mathrm{B}\textrm{-}\mathrm{ORG}$$ signifies the beginning of an organization's name, $$\mathrm{I}\textrm{-}\mathrm{ORG}$$ indicates a word inside an organization, and $$\mathrm{O}$$ means the word does not belong to any named entity. This specialization expands the total tag set size to $${}2 \times N + 1$$, where $$N$$ is the number of distinct entity classes.

Learn Before

Related

Learn After