Gaurav Sahu

Word Nerd. Sherlockologist. Vegan.

DC 2553

Univ. of Waterloo

Waterloo, Ontario, N2L 3G1

I am a Ph.D. student at the NLP Lab of the University of Waterloo, advised by Prof. Olga Vechtomova. My research focuses on multimodal deep learning and generative text modelling, where I explore ways to extract visual and auditory cues to generate better text. I am also interested in learning the dynamics of the shared multimodal latent space.

I am also a Visiting Researcher at ServiceNow Research, collaborating with the Human-Machine Interaction Through Language (HMITL) and the Low Data Learning (LDL) groups.

I earned a thesis-based M.Math. degree in Computer Science from the University of Waterloo. Prior to that, I got my B.Tech. degree in Manufacturing Science and Engineering from the Indian Institute of Technology Kharagpur (IIT Kharagpur), where I worked with Prof. Pawan Goyal on Program Synthesis for Natural Language.

Apart from research, I am much enthused by language and art. I love to sometimes engross myself with sketching and painting. Check out my art collection if you’d like! I have been learning to play the piano and to speak Japanese and French.

news

Mar 28, 2022 Our paper on data augmentation with LLMs accepted at NLP4ConvAI workshop at ACL 2022!
Jun 2, 2021 Our paper LyricJam got accepted to ICCC 2021 for oral presentation!
May 3, 2021 One paper on hate speech detection accepted at AASG workshop at AAMAS 2021.
Jan 11, 2021 My work on adaptive multimodal fusion methods accepted at EACL 2021 as a full paper!
Oct 1, 2020 One short paper on diverse dialog generation accepted at COLING 2020.
Sep 1, 2020 One paper on lyrics generation accepted at ISMIR’s NLP4MusA workshop.
Aug 28, 2020 Published my M.Math. Thesis.