Automatic Pattern Extraction

From Cohen Courses
Revision as of 18:09, 3 October 2011 by Manajs (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigationJump to search

Automatic Pattern Extraction is the task of automatically extracting linguistic patterns from a corpus to help in the task of Information Extraction from that corpus. Many semi-supervised methods like Pointwise Mutual Information and Bootstrapping have been used, in which a small set of manually identified seed patterns is used to automatically identify more relevant patterns for the particular task of IE.