Pedro Rodriguez

Pedro is a research scientist at Facebook Reality Labs in Seattle working on improving data collection and evaluation in Natural Language Processing. He completed his PhD in computer science at University of Maryland's CLIP lab in 2021, advised by Jordan Boyd-Graber. His dissertation explored ways to improve the data collection and evaluation methodologies in question answering. He was previously a research intern at Google AI-Zurich, FB Reality Labs, and Microsoft Research. Before his PhD and after completing his CS degree at UC Berkeley, he was a data scientist at Zillow Group.

Pedro's Publications

August 01, 2021

NLP

Evaluation Examples Are Not Equally Informative: How Should That Change NLP Leaderboards?

Leaderboards are widely used in NLP and push the field forward. While leaderboards are a straightforward ranking of NLP models, this simplicity can mask nuances in evaluation items …

Pedro Rodriguez, Joe Barrow, Alexander Hoyle, John P. Lalor, Robin Jia, Jordan Boyd-Graber

August 01, 2021