Hey everyone! Thank you so much for watching the 38th episode of the Weaviate podcast! This episode features Leo Boystov, an expert in Information Retrieval technology! We discussed a very wide range of topics from an overview of IR methods such as BM25, Neural Bi-Encoder and Cross-Encoder rankers, and a super exciting new work Leo has co-authored on using Large Language Models to generate training data for Neural Ranking models titled "InPars-Light: Cost-Effective Unsupervised Training of Efficient Rankers." We also discussed Leo's work on Non-Metric Space Search, the challenge of long document ranking, Robustness in Generalization Testing, and ended with some thoughts on Hybrid Rank Fusion. I really hope you enjoy the podcast, more than happy to answer any questions you have or clarify anything!
In-Pars Light: Cost-Effective Unsupervised Training of Efficient Rankers - https://arxiv.org/abs/2301.02998)
Google Scholar Leo Boystov - https://scholar.google.com/citations)?...
Chapters
0:00 Introduction
1:08 Information Retrieval Research
25:20 Ranker Inference Requirements
40:40 Non Metric Space Search
52:38 Code Libraries for IR Research
59:40 Long Document Ranking
1:07:00 Robustness Generalization
1:15:40 Hybrid Rank Fusion
