PROJECT TITLE :
A Boundary Assembling Method for Chinese Entity-Mention Recognition
ABSTRACT:
A boundary assembling (BA) methodology is presented for Chinese entity-mention recognition. Given a sentence, instead of recognizing entity mentions in a unitary style, the authors' BA methodology 1st detects boundaries of entity mentions and then assembles detected boundaries into entity-mention candidates. Each candidate is further assessed by a classifier trained on nonlocal features. This methodology can make higher use of nonlocal options and effectively recognize nested entity mentions. Using the ACE 2005 Chinese corpus, the authors' experimental results show an improvement over state-of-the-art techniques, outperforming existing methods in F-score by five percent for entity-mention detection and 4.23 percent for entity-mention recognition.
Did you like this research project? To get this research project Guidelines, Training and Code... Click Here |