Pranav A

I am Pranav and I am currently working as a Machine Learning Research Lead at Dayta AI. I graduated from Hong Kong University of Science and Technology studying Big Data Technology. My email is cs.pranav.a (at) gmail.com.

Github Link  /  LinkedIn Link  /  CV (Link to PDF)

Research Interests and Publications

Broadly, my interests are in NLP (Natural Language Processing) and AI ethics.

In the realm of NLP, my particular focus revolves around tokenization learning and multilinguality. Currently, my work centers on developing subword models in multilingual tasks, with a specific emphasis on addressing the following issues:

• How can we develop tokenization methods that effectively tackle the challenges of sparsity and skewness?
• How do different language families influence one another within multilingual datasets, and how can we leverage this knowledge to create improved tokenization methods tailored for multilingual models?

Regarding AI ethics, my main areas of interest include conference inclusivity, queerness in AI, and data sovereignty. Presently, my research efforts are concentrated on the following topics:

• How can community-based approaches enhance inclusivity at conferences?
• In cases where control over digital identity, as manifested in datasets, models, and algorithms, has been taken away from queer individuals, what tools can be devised to counteract this?
• Why do deadnames occur in citations of publications, and what tools can be developed to prevent the circulation of deadnames and outdated information?

Community-led participatory design case study of Queer in AI contributed lessons on decentralization, building community aid, empowering marginalized groups, and critiquing poor participatory practices.

Queer in AI provides a tutorial for diversity & inclusion organizers on making virtual conferences more queer-friendly through inclusivity based on their community's experiences with marginalization.

The paper contributes a contextual subword segmentation method along with benchmark datasets that outperformed previous Chinese character conversion approaches by 6 points in accuracy, especially for code-mixing and names entities.

The paper contributes information retrieval ranking functions with heuristics like positional tokenization and graphical error modelling to the problem of cognate detection.