Lecture notes: 13
Schedule, assessment and deadlines live in the course overview.
Lecture notes
- L02 IR Fundamentals
Information Retrieval, Inverted Index, Tokenization, Stemming, … - L03 Retrieval Models
TF-IDF, BM25, Query Likelihood Model, Language Model for IR, … - L04 Evaluation
Precision, Recall, F-Measure, MAP, … - L05 Neural IR Intro & Reranking
Neural Reranking, Cross-Encoder, Bi-Encoder, BERT for IR, … - L06 Dense Retrieval
Dense Retrieval, Bi-Encoder, DPR, ColBERT, … - L07 Learned Sparse Retrieval
Learned Sparse Retrieval, SPLADE, Document Expansion, Query Expansion, … - L08 Generative Retrieval
Generative Retrieval, Differentiable Search Index, Document Identifiers, Autoregressive Retrieval, … - L09 RAG
Retrieval-Augmented Generation, Dense Retrieval, Cross-Encoder, Transformers, … - L10 Learning to Rank
Learning to Rank, Pointwise LTR, Pairwise LTR, Listwise LTR, … - L11 Unbiased Learning to Rank
Learning to Rank, Click Models, Position Bias, Inverse Propensity Weighting, … - L12 IR and Society
Algorithmic Fairness, Exposure Fairness, Misinformation, Explainability, … - L13 RL for Reasoning and Search
Reinforcement Learning, Policy Gradient Methods, PPO, GRPO, … - L14 Triton and Sparton
GPU Architecture, Triton, Learned Sparse Retrieval, SPLADE, …
Book Notes
- PTR Ch1: Introduction
- PTR Ch2: Setting the Stage
- PTR Ch3: Multi-Stage Architectures for Reranking
- PTR Ch4: Refining Query and Document Representations
- PTR Ch5: Dense Retrieval and Learned Sparse Retrieval
- SEIRiP Ch4: Processing Text
- SEIRiP Ch5: Ranking with Indexes
- SEIRiP Ch7: Retrieval Models