Sequence Labeling for Parts of Speech and Named Entities

18.1 English word classes

1. Are parts of speech defined semantically?
   Not primarily: although classes have semantic tendencies, they are defined by grammatical relationships with neighboring words and by morphological properties of their affixes.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 401
2. What tagset does Universal Dependencies use?
   17 tags: open class ADJ, ADV, NOUN, VERB, PROPN, INTJ; closed class ADP, AUX, CCONJ, DET, NUM, PART, PRON, SCONJ; other PUNCT, SYM, X. Features can add finer distinctions (number, case…).

   open	closed	other
   NOUN VERB ADJ ADV PROPN INTJ	ADP AUX CCONJ DET NUM PART PRON SCONJ	PUNCT SYM X

   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 401
3. What is the difference between closed and open word classes?
   Closed classes (prepositions, determiners…) have relatively fixed membership, mostly short, frequent function words with grammatical uses. Open classes (nouns, verbs, adjectives, adverbs, interjections) constantly gain new members (iPhone, to fax).
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 401
4. What are function words?
   Closed-class words like of, it, and, you: very short, frequent, and often structuring the grammar.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 401
5. What grammatical properties characterize English nouns?
   They can occur with determiners (a goat), take possessives (IBM’s revenue), and may be plural (goats). Common nouns include concrete terms, abstractions and verb-like terms (his pacing).
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 401
6. What is the difference between count nouns and mass nouns?
   Count nouns have singular and plural and can be counted (one goat, two goats). Mass nouns denote something conceptualized as a homogeneous group and aren’t counted (snow, salt, communism; *two snows).
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 401
7. Do all languages distinguish nouns, verbs and adjectives?
   Not necessarily: some argue Riau Indonesian and Tongan don’t distinguish nouns and verbs; in Korean, words corresponding to English adjectives behave as a subclass of verbs (“to be beautiful”).
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 402
8. What are the main kinds of adverbs?
   Locative/directional (home, here), degree (extremely, very), manner (slowly, delicately), and temporal (yesterday, Monday). Adverbs modify verbs, other adverbs and whole verb phrases.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 402
9. What are interjections?
   A small open class: exclamations (oh, alas, um), greetings (hello), and question responses (yes, uh-huh).
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 402
10. What relations can English prepositions express?
    Spatial or temporal relations, literal (on it, before then) or metaphorical (on time, beside herself), and others like marking the agent (written by Shakespeare).
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 402
11. What is a particle, and what is a phrasal verb?
    A particle resembles a preposition or adverb but combines with a verb, often with an extended meaning (turned the paper over). A verb plus particle acting as a unit is a phrasal verb, often non-compositional (turn down = reject, rule out = eliminate).
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 402
12. What are determiners and articles?
    Determiners (this, that) can mark the start of a noun phrase; articles (a, an, the) are frequent determiners marking discourse properties of the noun.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 402
13. What is the difference between coordinating and subordinating conjunctions? What is a complementizer?
    Coordinating conjunctions (and, or, but) join elements of equal status. Subordinating conjunctions join a main clause with an embedded one. Those linking a verb to its clausal argument, like that in “I thought that you might like some milk”, are complementizers.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 402
14. What kinds of pronouns are there?
    Personal (you, she, it), possessive (my, their: possession or abstract relation), and wh-pronouns (what, who), used in questions or as complementizers.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, pp. 402–403
15. What do auxiliary verbs mark? Give English examples.
    Semantic features of the main verb: tense, aspect (completed?), polarity (negated?) and mood (necessary, possible, desired). English: the copula be, do, have, and modals like can, may, must.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 403
16. What is the Penn Treebank tagset?
    An English-specific tagset (36 core tags) used for many syntactically annotated corpora; unlike UD it distinguishes verb tenses and participles (VBD, VBN, VBG, VBZ…) and has a tag for existential there (EX).
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 403
17. How are the words of a multiword proper name like London Journal of Medicine tagged?
    Each component noun is tagged as a proper noun (PROPN/NNP), even journal and medicine.
    • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, §18.1, p. 403