Improving Question Answering
Sewon Min discusses the development of a two-stage framework for open domain question answering, focusing on improving the retrieval component. He explains how the dense passage retrieval method, which uses low-dimensional dense vectors to represent passages, can effectively identify relevant passages for answering questions without the need for large-scale label data or pretraining.In this clip
From this podcast

The Gradient
Sewon Min: The Science of Natural Language
Related Questions