Paper: DLUT: Chinese Personal Name Disambiguation with Rich Features

ACL ID W10-4160
Title DLUT: Chinese Personal Name Disambiguation with Rich Features
Venue Joint Conference on Chinese Language Processing
Session Main Conference
Year 2010
Authors

In this paper we describe a person clus- tering system for a given document set and report the results we have obtained on the test set of Chinese personal name (CPN) disambiguation task of CIPS- SIGHAN 2010. This task consists of clustering a set of Xinhua news docu- ments that mention an ambiguous CPN according to named entity in reality. Several features including named entities (NE) and common nouns generated from the documents and a variety of rules are employed in our system. This system achieves F = 86.36% with B_Cubed scoring metrics and F = 90.78% with pu- rity_based metrics.