Illinois CoRanker: an algorithm for NE discovery

(230 downloads)

[ Download | Key Publication | Questions/Comments ]

If you wish to cite this work, please use the following.

A. Klementiev and D. Roth, Weakly Supervised Named Entity Transliteration and Discovery from Multilingual Comparable Corpora. ACL  (2006) pp. USS,TL,ADAPT

This package contains an implementation of the CoRanking algorithm (presented at ACL 2006) for cross-lingual Named Entity discovery in bilingual weakly temporally aligned corpora.

Also see relvant data.

Participants:

Projects:

Demo: