|
 |
ISSN 1996-1065 [Online]
ISSN 1818-1139 [PRINT] |
|
|
Volume 2 (2) 2008 |
| Title: | Towards Domain Independent Named Entity Recognition |
| Authors: | Fredrick E.K. & Baryamureeba Venansius *,
Guy De Pauw |
| Published: |
ŠIJCIR Vol2 (2) 2008, PP. 84-95 |
| Language: | English |
Abstract:
Named entity recognition is a preprocessing tool to many natural language processing tasks, such as text
summarization, speech translation, and document ategorization. Many systems for named entity
recognition have been developed over the past years with substantial success save for the problem of being
domain specific and making it difficult to use the different systems across domains. This work attempts to
surmount the problem by proposing the use of domain independent features with a aximum entropy
model and a multiobjective genetic algorithm (MOGA) to select the best features. The methods used in this
work are backed up by experiments of which the classifications are evaluated using two diverse domains.
Conclusions are finally drawn and the outlook for future work is considered. View full Article
Categories and Subject Descriptors: I.2.7 [Artificial Intelligence]: Natural Language Processing—
language parsing and understanding; I.5.2 [Pattern Recognition]: Design Methodology— Feature
evaluation and selection
General Terms: Computer Science, Language Processing, Machine Learning
Additional Key Words and Phrases: domain independent, named entity recognition, multiobjective genetic
algorithm |
|
|
|
|
