Arun Kumar


2017

pdf
Morphological Analysis of the Dravidian Language Family
Arun Kumar | Ryan Cotterell | Lluís Padró | Antoni Oliver
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers

The Dravidian languages are one of the most widely spoken language families in the world, yet there are very few annotated resources available to NLP researchers. To remedy this, we create DravMorph, a corpus annotated for morphological segmentation and part-of-speech. Additionally, we exploit novel features and higher-order models to set state-of-the-art results on these corpora on both tasks, beating techniques proposed in the literature by as much as 4 points in segmentation F1.

2016

pdf
Morphological Segmentation Inside-Out
Ryan Cotterell | Arun Kumar | Hinrich Schütze
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2015

pdf
Learning Agglutinative Morphology of Indian Languages with Linguistically Motivated Adaptor Grammars
Arun Kumar | Lluís Padró | Antoni Oliver
Proceedings of the International Conference Recent Advances in Natural Language Processing

pdf
Unsupervised learning of agglutinated morphology using nested Pitman-Yor process based morpheme induction algorithm
Arun Kumar
Proceedings of the Student Research Workshop

pdf
Joint Bayesian Morphology Learning for Dravidian Languages
Arun Kumar | Lluís Padró | Antoni Oliver
Proceedings of the Joint Workshop on Language Technology for Closely Related Languages, Varieties and Dialects

2004

pdf
Statistical Language Modeling with Performance Benchmarks using Various Levels of Syntactic-Semantic Information
Dharmendra Kanejiya | Arun Kumar | Surendra Prasad
COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics

2003

pdf
Automatic Evaluation of Students’ Answers using Syntactically Enhanced LSA
Dharmendra Kanejiya | Arun Kumar | Surendra Prasad
Proceedings of the HLT-NAACL 03 Workshop on Building Educational Applications Using Natural Language Processing