Csci 4152: Statistical Natural Language Procesing

1
Linguistic Essentials
2
Parts of Speech and Morphology

• Parts of Speech correspond to syntactic or
  grammatical categories such as noun, verb,
  adjectives and prepositions.
• Word categories are systematically related by
  morphological processes such as the formation of
  plural form from the singular form.

3
Parts of Speech

• Nouns, verbs, adjectives
• Determiners
• Adverbs She ran very quickly She often travels
  to Vegas She started off impressively.
• Preposition She looked up the tree
• Particles She looked up the number
• Conjunctions, complementizer Funny but stupid She
  is afraid that .

4
Syntax or Phrase Structure A simple context-free
grammar

• S --gt NP VP
• NP --gt DT NNS
• DT NN
• NP PP
• VP --gt VP PP
• VBD
• VBD NP
• P --gt IN NP

• DT --gt the
• NNS --gt children
• students
• mountains
• VBD --gt slept
• ate
• saw
• IN --gt in
• of
• NN --gt cake

The Grammar
The Lexicon
5
Syntax or Phrase Structure A Parse Tree
S
NP VP AT
NNS VBD NP The
children ate AT NN

the cake
6
Local and Non-Local Dependencies

• Dependencies may be local e.g., DT NNS
• A non-local dependency is an instance in which
  two words can be syntactically dependent even
  though they occur far apart in a sentence (e.g.,
  subject-verb agreement wh-extraction).
• Non-local phenomena are a challenge for certain
  statistical NLP approaches (e.g., n-grams) that
  model local dependencies.

7
Semantic Roles

• Most commonly, noun phrases are arguments of
  verbs. These arguments have semantic roles the
  agent of an action, the patient and other roles
  such as the instrument or the goal.

8
Subcategorization

• Different verbs can relate different numbers of
  entities transitive versus intransitive verbs.
• Verbs are classified according to the type of
  complements they permit. This called
  subcategorization.
• FrameNet combines semantic roles and
  subcategorization. Lets look up put.v

9
Attachment Ambiguity and Garden-Path Sentences

• Attachment ambiguities occur with phrases that
  could have been generated by two different nodes
  in the parse tree. E.g. The
  children ate the cake with a spoon.
• Garden-Path sentences are sentences that lead you
  along a path that suddenly turns out not to
  work.
  E.g. The horse raced past the barn fell.

10
Semantics

• Semantics is the study of the meaning of words,
  constructions, and utterances.
• Semantics can be divided into two parts lexical
  semantics and combination semantics.
• Lexical semantics hypernymy, hyponymy, antonymy,
  meronymy, holonymy, synonymy, homonymy, polysemy,
  and homophony (no need to memorize!).
• Compositionality the meaning of the whole is
  built up from the meanings of its parts language
  is often not compositional, though.
• Idioms correspond to cases where the compound
  phrase means something completely different
  from its parts.

11
Pragmatics

• Pragmatics is the area of studies that goes
  beyond the study of the meaning of a sentence and
  tries to explain what the speaker really is
  expressing.
• Understand the scope of quantifiers, speech acts,
  discourse analysis, anaphoric relations.