This paper describes a new system called \Maximum Entropy Named Entity" or \MENE" (pronounced \meanie") which was NYU's entrant in the MUC-7 named entity evaluation. By working within the framework of maximum entropy theory and utilizing a exible object-based architecture, the system is able to make use of an extraordinarily diverse range of knowledge sources in making its tagging decisions. These knowledge sources include capitalization features, lexical features and features indicating the current type of text (i.e. headline or main body). It makes use of a broad array of dictionaries of useful single or multi-word terms such as rst names, company names, and corporate su xes. These dictionaries required no manual editing and were either downloaded from the web or were simply \obvious" lists entered by hand.
[1]
Adwait Ratnaparkhi,et al.
A Simple Introduction to Maximum Entropy Models for Natural Language Processing
,
1997
.
[2]
Ralph Grishman,et al.
The NYU System for MUC-6 or Where’s the Syntax?
,
1995,
MUC.
[3]
Richard M. Schwartz,et al.
Nymble: a High-Performance Learning Name-finder
,
1997,
ANLP.
[4]
Dekang Lin.
Using Collocation Statistics in Information Extraction
,
1998,
MUC.