NLP's Future Directions
Richard discusses the evolution of natural language processing, emphasizing the shift towards large, general function approximators and the importance of objective functions over traditional feature engineering. He envisions a future where advancements in NLP contribute to a cumulative improvement in supermodels, leading to significant progress in the field. The conversation highlights the excitement surrounding multitask models and the gradual acceptance of these new methodologies within the research community.In this clip
From this podcast
Gradient Dissent - A Machine Learning Podcast
Richard Socher — The Challenges of Making ML Work in the Real World
Related Questions