Difference between revisions of "Named entity recognizers"

Revision as of 18:34, 3 April 2010

Software - Named entity recognizers

Balie Baseline implementation of named entity recognition.
GATE includes the ANNIE gazeteer-based NER subsystem.
GENiA- part-of-speech tagging, shallow parsing, and named entity recognition for biomedical text. C++, BSD license.
Greek named entity recognizer (version 2) It currently identifies temporal expressions, person names, and organization names; see here for publications describing the recognizer.
LingPipe
Stanford NER Conditional Random Fields based NER. Also incorporates distributional similarity based features extracted from the English Gigaword corpus.
Illinois NER Java-based Illinois NER tagger. Uses gazetteers extracted from Wikipedia, word-class model built from unlabeled text and extensively uses non-local features. Achieves 90.8F1 score on the CoNLL03 shared task data and is robust on other datasets. Try the Illinois-NER-Demo
Older version of Illinois NER - identifies/classifies entities as Person, Location, Organization and Misc (this last category relates to languages and nationalities); fast and robust; try the demo

@@ Line 7: / Line 7: @@
 *[http://www.alias-i.com/lingpipe/ LingPipe]
 *[http://nlp.stanford.edu/software/CRF-NER.shtml Stanford NER] Conditional Random Fields based NER. Also incorporates distributional similarity based features extracted from the English Gigaword corpus.
-*[http://l2r.cs.uiuc.edu/~cogcomp/asoftware.php?skey=FLBJNE Illinois NER] Java-based Illinois NER tagger. Uses gazetteers extracted from Wikipedia, word-class model built from unlabeled text and extensively uses non-local features. Achieves 90.8F1 score on the CoNLL03 shared task data and is robust on other datasets. Try the [http://l2r.cs.uiuc.edu/~cogcomp/LbjNer.php LBJ-NER-Demo]
+*[http://l2r.cs.uiuc.edu/~cogcomp/asoftware.php?skey=FLBJNE Illinois NER] Java-based Illinois NER tagger. Uses gazetteers extracted from Wikipedia, word-class model built from unlabeled text and extensively uses non-local features. Achieves 90.8F1 score on the CoNLL03 shared task data and is robust on other datasets. Try the [http://l2r.cs.uiuc.edu/~cogcomp/LbjNer.php Illinois-NER-Demo]
 * [http://l2r.cs.uiuc.edu/~cogcomp/asoftware.php?skey=NE Older version of Illinois  NER] - identifies/classifies entities as Person, Location, Organization and Misc (this last category relates to languages and nationalities); fast and robust; try the [http://l2r.cs.uiuc.edu/~cogcomp/ne_demo.php demo]
 [[Category:Software]]