Save this video free

UUtah CS 6340 NLP | Fall 2026 | Retrieval (cont.) & Answer extraction

UofU Data Science · 1:19:29 · Watch on YouTube

Part of University of Utah CS 6340. See all 19 lectures and search them

These notes were made with YouTube Collector. Paste any YouTube link and get the same: a summary, chapters and a searchable transcript.

Overview

The lecture connects large-scale retrieval to answer generation and extraction, reviewing BM25 and dense retrieval before explaining approximate nearest-neighbor search with Faiss, retrieval metrics such as F1 and mean reciprocal rank, and design choices for retrieval-augmented systems. It then derives BERT-style answer extraction using learned start and end vectors, negative log-likelihood training, no-answer and long-passage handling, and token-level F1, before contrasting extractive answers with retrieval-augmented generation (RAG).

Key takeaways

Chapters

0:00 Course Logistics, Quiz Scope, and Practical Assignment Feedback
5:10 Open-Ended QA, BM25, DPR, and ColBERT Recap
10:44 Maximum Inner Product Search and Approximate Nearest Neighbors
13:04 K-Means Clusters as a Dense Retrieval Index
22:07 Faiss IVF Configuration, Search Parameters, and Vector Compression
25:34 Retrieval Evaluation with Precision, Recall, F1, and MRR
32:10 Retrieval Design: Chunks, Entities, Memories, and Timing
42:00 Similarity Choices and Questions About ANN Search
48:39 BERT Answer Extraction Predicts a Span Instead of Generating Text
53:00 Start and End Probability Distributions over Passage Tokens
1:01:30 Negative Log-Likelihood Training and Span Inference
1:09:06 Handling Missing Answers and Passage Length Limits
1:12:14 Answer Extraction Metrics and the Hugging Face Training Notebook
1:15:00 Retrieval-Augmented Generation Combines Evidence with Next-Token Prediction
1:17:20 Choosing Extraction for High-Risk, Low-Hallucination Applications

Keep these chapters and the full searchable transcript in your own library.

Transcript excerpt

0:00 Good afternoon, everyone. Um hope you had a nice weekend. Uh I sent an announcement about bonuses and how I will count them for quizzes. So, if you haven't seen that announcement, it's posted on Canvas. Uh so, check that out. Um Uh yeah, I don't have much more to say about that. Are there any questions uh about the announcement or anything else um logistics-wise or not? Yeah, go ahead. >> Have you updated on the previous quizzes yet? >> Uh not not yet. Jonathan is attending EMNLP, one of our conferences, so uh I doubt they're going to be done this week. Uh but, we'll try to get them done soon when he's back. Yeah, sorry about that.

0:48 Yes, please. >> The bonus we added both quizzes for the second quiz. >> Um read the announcement. If it's unclear, ask me. Uh the formula is right there, so I think it's easiest to just read the formula. Yeah. Yeah. Yeah. >> Okay. Well, I'll do fine on the last three. How How well did you do on the first one? >> How How well are they doing? Um well, we graded um you mean the second one? >> Yes, yes, that. >> Uh we don't I don't discuss the intermediate grading with uh yeah, so I wouldn't know that. Yeah, we we discuss them once everything is graded, so I have no information about that. Yeah. But, Lucas, maybe you can >> I thought the grading was pretty good overall. >> Yeah. But, that can be sampling.

1:38 What do you say? With uh teaching experience comes, don't give any high hopes. I I can't even I I I felt the second one, the vibes were in the room generally, I would say better than for on the first one. So, my expectation is

This is the start of the transcript. Save this video free for the whole transcript, searchable and time-coded.

In this course

Related notes

Summary, takeaways, and chapters were generated by AI from the video's transcript and may contain errors. The video belongs to its creator, UofU Data Science.

Want the full transcript?

Save this video in YouTube Collector to get its complete searchable transcript, your own AI summaries, and a library that keeps every video you collect in one place.