Hi! I'm Lj Miranda, and welcome to my website!
I'm broadly interested in building equitable language technologies in the presence of severe data and compute constraints. I'm happy to discuss research and collaborate, so feel free to reach out!
While cloning a repository from an organization, I encountered an SSH error that I've never seen before. It's something related to SAML SSO. I managed to solve it, so I'm documenting the steps here. Hope it helps you too!
Lately, I've been thinking a lot about visualizing datasets, and good old-fashioned t-SNE embeddings came to mind. In this blog post, indulge me as I examine a "data map" of our Tagalog NER dataset.
Large language models showed promise on structured prediction tasks like named entity recognition and text categorization. But how well do they perform when presented with Tagalog text? In this blog post, I'll share some of my preliminary benchmarking results.