Sequence Labeling for Parts of Speech and Named Entities

18.3 Named entities

1. How does the semantic notion of named entity differ from the grammatical notion of proper noun?
   POS tagging says Janet, Stanford University, Colorado are proper nouns; NER says what kind of entity each refers to: person, organization, location.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.3, p. 405
2. What is named entity recognition, and what types are most common?
   Finding spans of text that are proper names and tagging their type: PER, LOC, ORG, GPE; often extended to dates, times and prices.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.3, p. 405
3. Name tasks for which named entity tagging is a useful first step.
   Entity-directed sentiment analysis, question answering, linking text to knowledge bases like Wikipedia, and extracting events and relations between participants.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.3, p. 405
4. Why is NER harder than POS tagging?
   It has a segmentation problem (finding entity spans and their boundaries, when most words aren’t entities) and type ambiguity (JFK as person, airport, school…).
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.3, p. 406
5. What is BIO tagging, and how many tags does it need?
   B for the first token of a span, I for tokens inside a span, O outside; with B and I per entity type, \(2n + 1\) tags for \(n\) types. It turns span recognition into per-token labeling.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.3, p. 406
6. What do the IO and BIOES schemes change?
   IO drops B (losing boundaries between adjacent entities); BIOES adds E for a span’s last token and S for single-token spans.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.3, p. 406