Back to Search
Start Over
Enhancing the Performance of Telugu Named Entity Recognition Using Gazetteer Features.
- Source :
-
Information (2078-2489) . Feb2020, Vol. 11 Issue 2, p82. 1p. - Publication Year :
- 2020
-
Abstract
- Named entity recognition (NER) is a fundamental step for many natural language processing tasks and hence enhancing the performance of NER models is always appreciated. With limited resources being available, NER for South-East Asian languages like Telugu is quite a challenging problem. This paper attempts to improve the NER performance for Telugu using gazetteer-related features, which are automatically generated using Wikipedia pages. We make use of these gazetteer features along with other well-known features like contextual, word-level, and corpus features to build NER models. NER models are developed using three well-known classifiers—conditional random field (CRF), support vector machine (SVM), and margin infused relaxed algorithms (MIRA). The gazetteer features are shown to improve the performance, and theMIRA-based NER model fared better than its counterparts SVM and CRF. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 20782489
- Volume :
- 11
- Issue :
- 2
- Database :
- Academic Search Index
- Journal :
- Information (2078-2489)
- Publication Type :
- Academic Journal
- Accession number :
- 142068896
- Full Text :
- https://doi.org/10.3390/info11020082