Neural Search Talks  — Transformer Memory as a Differentiable Search Index
In this episode of Neural Information Retrieval Talks, Andrew Yates and Sergi Castella discuss the paper titled "Transformer Memory as a Differentiable Search Index" by Yi Tay et al. at Google.
This work proposes a new approach to document retrieval in which document ids are memorized by a transformer during training (or "indexing") and for retrieval, a query is fed to the model, which then generates autoregressively relevant doc ids for that query.
Listen on other platforms: https://anchor.fm/neural-ir-talks/episodes/Transformer-Memory-as-a-Differentiable-Search-Index-memorizing-thousands-of-random-doc-ids-works-e1g4b4v
00:00 Intro: Transformer memory as a Differentiable Search Index (DSI)
01:15 The gist of the paper, motivation
4:20 Related work: Autoregressive Entity Linking
7:38 What is an index? Conventional vs. "differentiable"
10:20 Indexing and Retrieval definitions in the context of the DSI
12:40 Learning representations for documents
17:20 How to represent document ids: atomic, string, semantically relevant
22:00 Zero-shot vs. finetuned settings
24:10 Datasets and baselines
27:08 Dinetuned results
36:40 Zero-shot results
43:50 Ablation results
47:15 Where could this model be useds?
52:00 Is memory efficiency a fundamental problem of this approach?
55:14 What about semantically relevant doc ids?
60:30 Closing remarks