Harsh Jhamtani

jharsh@cmu.edu

I'm a PhD student at LTI, School of Computer Science, Carnegie Mellon University working in NLP/ML. My research interests are primarily in interpretable neural methods for grounded text generation.

Publications

Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation. (Short Paper)
Harsh Jhamtani *, Varun Gangal *, Eduard Hovy, Taylor Berg-Kirkpatrick Findings of ACL 2021
[pdf]
Unsupervised Enrichment of Persona-grounded Dialog with Background Stories. (Short Paper)
Bodhisattwa P. Majumder, Taylor Berg-Kirkpatrick, Julian McAuley, Harsh Jhamtani ACL 2021
[pdf]
Thesis Proposal
Harsh Jhamtani. Nov 2020
[pdf]
Modeling Self-Repetition in Music Generation using Generative Adversarial Networks.
Harsh Jhamtani, Taylor Berg-Kirkpatrick Machine Learning for Music Discovery Workshop. ICML 2019
[pdf]
SPINE - Sparse Interpretable Neural Embeddings.
H. Jhamtani, D. Pruthi, A. Subramanian, T. Berg-Kirkpatrick, and E. Hovy. AAAI 2018.
[pdf]