
Shrimai Prabhumoye
Carnegie Mellon Univeristy, USA
natural language generation
controllable text generation
neural text generation
2
presentations
2
number of views
SHORT BIO
Shrimai Prabhumoye is a Research Scientist at Nvidia. She obtained her PhD from Carnegie Mellon University (CMU) and worked with Prof. Alan W Black and Prof. Ruslan Salakhutdinov. Her research is centered around making machines sound more human-like. Specifically, her thesis focused on controlling style, content and structure in text generation and the ethical considerations of this technology. She has numerous publications in top tier AI conferences like ACL, NAACL and EMNLP. She has been invited for talks at Google, Apple, Salesforce, Allen Institute for AI (AI2), MILA and University of Massachusetts Amherst on this subject. Her research has featured in multiple media outlets like TechCrunch, Pittsburgh Post-Gazette, CNET, and MSN. She was also the co-designer of the Computational Ethics for NLP course offered at CMU. Before her PhD, she obtained a masters in language technologies at CMU where she lead the CMU Magnus team in the Alexaprize competition in 2017.
Presentations

Focused Attention Improves Document-Grounded Generation
Shrimai Prabhumoye and 4 other authors

Exploring Controllable Text Generation Techniques
Shrimai Prabhumoye and 2 other authors