Abstract: Embeddings are numerical representations of concepts converted to number sequences, which make it easy for computers to understand the relationships between those concepts. This talk will focus on introducing embeddings that is useful to perform natural language and code tasks like semantic search, clustering, topic modeling, and classification. Our embeddings available in the OpenAI API and outperform top models in 3 standard benchmarks, including a 20% relative improvement in code search.
Bio: Arvind Neelakantan is a Research Lead and Manager at OpenAI working on deep learning research for real-world applications. He got his PhD from UMass Amherst where he was also a Google PhD Fellow. His work has received best paper awards at NeurIPS and at Automated Knowledge Base Construction workshop.