A Memory-Based Learning Approach for Named Entity Recognition in Hindi

摘要

Named entity (NE) recognition (NER) is a process to identify and classify atomic elements such as person name, organization name, place/location name, quantities, temporal expressions, and monetary expressions in running text. In this paper, the Hindi NER task has been mapped into a multiclass learning problem, where the classes are NE tags. This paper presents a solution to this Hindi NER problem using a memory-based learning method. A set of simple and composite features, which includes binary, nominal, and string features, has been defined and incorporated into the proposed model. A relatively small Hindi Gazetteer list has also been employed to enhance the system performance. A comparative study on the experimental results obtained by the memory-based NER system proposed in this paper and a hidden Markov model (HMM)-based NER system shows that the performance of the proposed memory-based NER system is comparable to the HMM-based NER system.