Premium
Colorless green ideas learn furiously: Chomsky and the two cultures of statistical learning
Author(s) -
Norvig Peter
Publication year - 2012
Publication title -
significance
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.123
H-Index - 21
eISSN - 1740-9713
pISSN - 1740-9705
DOI - 10.1111/j.1740-9713.2012.00590.x
Subject(s) - nothing , causation , computer science , artificial intelligence , statistical analysis , natural language processing , linguistics , cognitive science , epistemology , psychology , philosophy , mathematics , statistics
Language recognition programs use massive databases of words, and statistical correlations between those words, to translate or to recognise speech. But correlation is not causation. Do these statistical data‐dredgings give any insight into how language works? Or are they a mere big‐number trick, useful but adding nothing to understanding? One who holds the latter view is the theorist of language Noam Chomsky. Peter Norvig disagrees.