Dependency Parsing

Introduction

1. How do dependency grammars describe syntactic structure?
   Solely as directed binary grammatical relations between words, with arcs from heads to dependents; phrasal constituents and phrase-structure rules play no direct role.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 20, Introduction, p. 449
2. What is a typed dependency structure, and what is the root?
   A dependency structure whose arc labels come from a fixed inventory of grammatical relations. A root node marks the head of the entire structure.

   “I prefer the morning flight through Denver”

   word	head	relation
   I	prefer	nsubj
   prefer	ROOT	root
   the	flight	det
   morning	flight	compound
   flight	prefer	obj
   through	Denver	case
   Denver	flight	nmod

   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 20, Introduction, p. 449
3. Why are dependency grammars popular in NLP?
   Head–dependent relations directly encode information buried in phrase-structure trees, such as predicate–argument relations (the arguments of prefer link straight to it); they are a good proxy for semantic relations. They also handle free word order well.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 20, Introduction, pp. 449–450
4. Why do dependency grammars suit languages with free word order like Czech?
   A phrase-structure grammar needs a separate rule for each position where, say, an adverbial could appear; a dependency grammar needs just one link type for that relation, abstracting away from word order.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 20, Introduction, p. 450