Gaurav Kumar

226 Hackerman Hall
Center for Language and Speech Processing
Johns Hopkins University

Research Statement

I am a Ph.D. candidate in Computer Science at Johns Hopkins University (JHU), advised by Dr. Philipp Koehn and Dr. Sanjeev Khudanpur. I am a research member of the Center for Language and Speech Processing (CLSP) and the Human Language Technology Center of Excellence (HLTCOE) at JHU. I work on Machine Learning for Natural Language Processing (NLP) and Speech Recognition and my recent work has focused on the intersection of NLP and Reinforcement Learning (RL) for Meta (Curriculum) Learning.

I have been a research intern at Google AI and at the IBM T.J. Watson Research Center. I also hold a Masters and Bachelors in Computer Science from Johns Hopkins and VIT University, respectively.


Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora (arXiv preprint, 2021) | Gaurav Kumar, Philipp Koehn, and Sanjeev Khudanpur

Learning Policies for Multilingual Training of Neural Machine Translation Systems (arXiv preprint, 2021) | Gaurav Kumar, Philipp Koehn, and Sanjeev Khudanpur

Reinforcement Learning based Curriculum Optimization for Neural Machine Translation (NAACL, 2019) | Gaurav Kumar, George Foster, Colin Cherry and Maxim Krikun

Curriculum Learning for Domain Adaptation in Neural Machine Translation (NAACL, 2019) | Xuan Zhang, Pamela Shapiro, Gaurav Kumar, Paul McNamee, Marine Carpuat and Kevin Duh

An Empirical Exploration of Curriculum Learning for Neural Machine Translation (arXiv preprint, 2018) | Xuan Zhang, Gaurav Kumar, Huda Khayrallah, Kenton Murray, Jeremy Gwinnup, Marianna J Martindale, Paul McNamee, Kevin Duh and Marine Carpuat

Neural Lattice Search for Domain Adaptation in Machine Translation (IJCNLP, 2018) | Huda Khayrallah, Gaurav Kumar, Kevin Duh, Matt Post and Philipp Koehn

Using of heterogeneous corpora for training of an ASR system (arXiv preprint, 2017) | Jan Trmal, Gaurav Kumar, Vimal Manohar, Sanjeev Khudanpur, Matt Post and Paul McNamee

DyNet: The Dynamic Neural Network Toolkit (arXiv preprint, 2017) | Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Paul Michel, Yusuke Oda, Matthew Richardson, Naomi Saphra, Swabha Swayamdipta and Pengcheng Yin

The JHU Machine Translation Systems for WMT 2017 (WMT, 2017) | Shuoyang Ding, Huda Khayrallah, Philipp Koehn, Matt Post, Gaurav Kumar and Kevin Duh

A Coarse-Grained Model for Optimal Coupling of ASR and SMT Systems for Speech Translation (EMNLP, 2015) | Gaurav Kumar, Graeme Blackwood, Jan Trmal, Daniel Povey and Sanjeev Khudanpur

Joshua 6: A phrase-based and hierarchical statistical machine translation system (Prague Bulletin of Mathematical Linguistics, 2015) | Matt Post and Yuan Cao and Gaurav Kumar

Translations of the CALLHOME Egyptian Arabic Corpus for Conversational Speech Translation (IWSLT, 2014) | Gaurav Kumar, Yuan Cao, Ryan Cotterell, Chris Callison-Burch, Daniel Povey and Sanjeev Khudanpur

Some Insights from Translating Conversational Telephone Speech (ICASSP, 2014) | Gaurav Kumar, Matt Post, Daniel Povey and Sanjeev Khudanpur

Improved Speech-to-Text Translation with the Fisher and Callhome Spanish--English Speech Translation Corpus (IWSLT, 2013) | Matt Post, Gaurav Kumar, Adam Lopez, Damianos Karakos, Chris Callison-Burch and Sanjeev Khudanpur


A Stack-based Algorithm for Neural Lattice Rescoring (CLSP Seminar, JHU, Apr 2017) pdf

Tensorflow tutorial (NMT Winter School, JHU, Jan 2017) pdf

Machine Translation and Neural Networks (CLSP Seminar, JHU, Mar 2015) pdf

Automatic Text Message based Vaccination Reminders to Improve Compliance (Southern Society for Pediatric Research, 2015) | Akshay Sharma, Anil P. George, Parvathi Nataraj, Katherine E. Wimberly, Gaurav Kumar, Kimberly Northrip

Learning about transitions: Adaptive Controls for the Molecular Dynamics Database (58th Annual Meeting of the Biophysical Society, 2014) | Sarana Nutanong, Yanif Ahmad, I-Jeng Wang, Jeliazko Jeliazkov, Gaurav Kumar and Thomas B. Woolf

Other things

I am a Trustee at the Immunize India Charitable Trust which provides immunization services to children in India.

Find me on Goodreads.