Named Entity Recognition (NER) for Telugu is a challenging task due to the characteristic features of the language. Earlier studies have made use of handcrafted features and gazetteers for identifying named entities (NEs). In this paper, we present a Long Short-Term Memory (LSTM) - Conditional Random Fields (CRF) based approach that does not use any handcrafted features or gazetteers. The results are compared to those of traditional classifiers like support vector machines (SVMs) and CRFs. The LSTM-CRF classifier performs significantly better than both of them, achieving an F-measure of 85.13%.
@InProceedings{REDDY18.2, author = {Aniketh Janardhan Reddy ,Monica Adusumilli ,Sai Kiranmai Gorla ,Lalita Bhanu Murthy Neti and Aruna Malapati}, title = {Named Entity Recognition for Telugu using LSTM-CRF}, booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {may}, date = {7-12}, location = {Miyazaki, Japan}, editor = {Girish Nath Jha and Kalika Bali and Sobha L and Atul
Kr. Ojha}, publisher = {European Language Resources Association (ELRA)}, address = {Paris, France}, isbn = {979-10-95546-09-2}, language = {english} }
Summary of the paper