Tanuja Ganu

Predicting the Performance of Multilingual NLP Models

2021 · arXiv (Cornell University)

Recent advancements in NLP have given us models like mBERT and XLMR that can serve over 100 languages. The languages that these models are evaluated on, however, are very few in number, and it is …

TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning

2024 · arXiv (Cornell University)

Spatial representation learning (SRL) aims at learning general-purpose neural network representations from various types of spatial data (e.g., points, polylines, polygons, networks, images, etc.) in their native formats. Learning good spatial representations is a fundamental …