Sequence Labeling for Parts of Speech and Named Entities

Introduction

1. Where does the traditional list of eight parts of speech come from?
   From the grammatical sketch of Greek attributed to Dionysius Thrax (c. 100 B.C.): noun, verb, pronoun, preposition, adverb, conjunction, participle, article. It became the basis for describing European languages for 2000 years.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, Introduction, p. 400
2. Why are parts of speech and named entities useful?
   They are clues to structure and meaning: a word’s POS predicts its neighbors (determiners before nouns) and syntactic links (verbs to nouns), making tagging key for parsing; knowing whether Washington is a person, place or university matters for QA, stance detection and information extraction.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, Introduction, p. 400
3. What is a sequence labeling task?
   Assigning each word \(x_i\) of an input sequence a label \(y_i\), so the output has the same length as the input; e.g. POS tagging and NER.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, Introduction, p. 400
4. Which two classic sequence labeling algorithms does the chapter introduce?
   The generative Hidden Markov Model (HMM) and the discriminative Conditional Random Field (CRF).
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 18, Introduction, p. 400