
[32] Andre Martins - The Geometry of Constrained Structured Prediction
The Thesis Review
00:00
Journey Through Machine Learning and NLP
This chapter chronicles the speaker's evolution in the field of machine learning, from their initial focus on computer vision to a deep dive into natural language processing (NLP) during their PhD. They discuss the challenges of structured prediction, contrasting traditional and modern approaches, and the role of constraints in enhancing model accuracy. The conversation broadens to include the philosophical implications of problem-solving within NLP, particularly the integration of AI systems and human communication.
Transcript
Play full episode