Rahul Aralikatte

I am a Ph.D student in the CoAStaL NLP group at the University of Copenhagen working with Prof. Anders Søgaard. My area of research is Natural Language Understanding. I work on improving coreference resolution and other shallow semantic parsing systems using external knowledge and downstream rewards. I am funded by a Google Focused Research Award.


Selected Publications

Rewarding Coreference Resolvers for Being Consistent with World Knowledge

Rahul Aralikatte, Heather Lent, Ana Valeria Gonzalez, Daniel Herschcovich, Chen Qiu, Anders Sandholm, Michael Ringgaard, Anders Søgaard. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP). Hong Kong, China. [pdf][code]

Compositional Generalization in Image Captioning

Mitja Nikolaus, Mostafa Abdou, Matthew Lamm, Rahul Aralikatte, Desmond Elliott. Proceedings of the 2019 SIGNLL Conference on Computational Natural Language Learning (CoNLL). Hong Kong, China. [pdf][code]

Adversarial Black-Box Attacks for Automatic Speech Recognition Systems Using Multi-Objective Evolutionary Optimization

Shreya Khare, Rahul Aralikatte, Senthil Mani Proceedings of the 20th Annual Conference of the International Speech Communication Association (Interspeech). Graz, Austria. [pdf]

Sanskrit Sandhi Splitting using seq2(seq)2

Rahul Aralikatte, Neelamadhav Gantayat, Naveen Panwar, Anush Sankaran, Senthil Mani. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP). Brussels, Belgium. [pdf]

DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension

Amrita Saha, Rahul Aralikatte, Mitesh M. Khapra, Karthik Sankaranarayanan Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL). Melbourne, Australia. [pdf][data]


Previous employers