Concept - Word Sense Disambiguation

Definition: determining which sense of an ambiguous word is meant in context. Slide example (s.49): disambiguate bank in “The bank can guarantee deposits will eventually cover future tuition costs because it invests in adjustable-rate mortgage securities”, given two Concept - WordNet senses: bank^1 (financial institution that accepts deposits and channels money into lending) and bank^2 (sloping land beside a body of water).

Methods on the slides

  • Concept - Lesk Algorithm (Simplified Lesk): choose the sense with the most word overlap between gloss and context, ignoring stop words (s.50); NLTK lesk returns the Synset with most overlapping words (s.51).
  • Babelfy (s.52): state-of-the-art system based on the BabelNet multilingual semantic network; does multilingual WSD and Entity Linking.

Also listed with POS tagging and parsing as part of syntactic analysis (s.43).

Concept - WordNet | Concept - Lesk Algorithm | Concept - Word Sense Relations | Concept - POS Tagging

Source: 02 Pre-processing - Chunk 02 (s.31-60)