Mohd 'Sanad' Zaki Rizvi

I’m a Graduate Student Researcher at the University of Edinburgh, where I focus on enhancing factual and faithful reasoning in large language models, advised by Dr. Pasquale Minervini.

Previously, I worked at Google Research India with Dr. Partha Talukdar, concentrating on entity-aware and neural speech translation to improve cross-lingual video access for low-resource languages.

Before that, I was with Microsoft Research India, where I developed tools for language identification and code-mixed text generation under the guidance of Dr. Monojit Choudhury, Dr. Sunayana Sitaram, Dr. Kalika Bali and Tanuja Ganu.

My early career involved diverse roles, including a Data Scientist position at Analytics Vidhya, where I co-instructed NLP MOOCs and authored popular technical blogs on Data Science, ML, NLP and AI.

selected publications

EACL

GCM: A Toolkit for Generating Synthetic Code-mixed Text

Mohd Sanad Zaki Rizvi, Anirudh Srinivasan, Tanuja Ganu, and 2 more authors

In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, Apr 2021

Abs DOI

Code-mixing is common in multilingual communities around the world, and processing it is challenging due to the lack of labeled and unlabeled data. We describe a tool that can automatically generate code-mixed data given parallel data in two languages. We implement two linguistic theories of code-mixing, the Equivalence Constraint theory and the Matrix Language theory to generate all possible code-mixed sentences in the language-pair, followed by sampling of the generated data to generate natural code-mixed sentences. The toolkit provides three modes: a batch mode, an interactive library mode and a web-interface to address the needs of researchers, linguists and language experts. The toolkit can be used to generate unlabeled text data for pre-trained models, as well as visualize linguistic theories of code-mixing. We plan to release the toolkit as open source and extend it by adding more implementations of linguistic theories, visualization techniques and better sampling techniques. We expect that the release of this toolkit will help facilitate more research in code-mixing in diverse language pairs.
JRTE

Feasibility and usability of MentorPal, a framework for rapid development of virtual mentors

Benjamin D. Nye, Dan M. Davis, Sanad Z. Rizvi, and 4 more authors

Journal of Research on Technology in Education, Apr 2021

DOI