Jordan Boyd-Graber

Jordan Boyd-Graber
4146 Iribe
Computer Science
jbg@boydgraber.org

How and Why Artificial Intelligence Answers Questions (CMSC 848Q)

Logistics

Location	CSIC 3117
Time	Mon./Wed. 14:00am - 15:15pm
Webpage	http://umiacs.umd.edu/~jbg/teaching/CMSC_848/
Homework Submission	https://www.gradescope.com/courses/303336
Mailing List	http://piazza.com/umd/spring2022/cmsc848q/home
Syllabus	https://docs.google.com/document/d/1VaIUHiEVU6dZ6y8uega-Z4SV6R4KdFSNkbXAo4V5Dck/edit?usp=sharing

People

Professor

Jordan Boyd-Graber
IRB 4146
Office Hours (IRB 4146): By appointment

Teaching Assistant

Maharshi Gor: Office Hours

Schedule

Date	In-Class Topic	Assignment Due
Mon 24. Jan	Introducing the Course
	Lecture: Structure of the course, why QA is important [Slides] How to take a class with me [Slides] Class in the Time of Corona [Slides] Hybrid classes Reading: Chapter 1 of Question Answering for the Curated Web Tasks and Methods in QA over Knowledge Bases and Text Collections (Alternate link)
Wed 26. Jan	QA History / Background
	How question answering saved civilization [Slides, including Turing Test] What AI Researchers can Learn from Trivia Nerds [Slides] A history of recreational question answering [Slides] The Turing Test Watson on Jeopardy! [Slides] Reading: Introduction to Braniac Turing's Two Tests for Intelligence The Watson Project
Mon 31. Jan	Information Retrieval / tf-idf
	Lecture: What is information retrieval? [Slides] Evaluation [Slides] The Cranfield Paradigm [Slides] TF-IDF [Slides] Readings: IR Chapter 1, 6 Evolution of Cranfield (Alternate link)
Wed 2. Feb	History of Computational Question Answering
	Lecture: GOFAI Approaches for QA [Slides] Statistical QA / Watson KB QA Readings: NLQA: The View from Here Chapter 3 of Question Answering for the Curated Web Tasks and Methods in QA over Knowledge Bases and Text Collections (Alternate link)
Fri 4. Feb	Homework Due	HW0
Mon 7. Feb	Neural Sequence Models for Language
	Lecture: Distributional Semantics [Slides] Word2Vec [Slides] RNN LSTM Neural Language Models [Slides] BERT [Slides] Readings: SNLP Chapter 9 (Optional) The Annotated Transformer
Wed 9. Feb	QA Datasets
	Lecture: QA Datasets [Slides] [Slides] Cranfield vs. Manchester [Slides] Multihop [Slides] Readings: SNLP 23 (Optional) Taxonomy of NLP QA
Fri 11. Feb	Homework Due	HW1
Mon 14. Feb	Computational Frameworks
	Lecture: Frameworks [Slides] Pytorch [Slides] DAN [Sildes] Reading: Minitorch (Up to autodiff)
Wed 16. Feb	Machine Reading
	Dr. QA [Slides] Dense Retrieval [Slides] BERT for MRQA Multihop Reading: MRC Literature Review
Mon 21. Feb	Paper Presentations I (ALL ZOOM)
Wed 23. Feb	Beyond Factoid QA: Generation, Conversational, Long-form QA
	Generation for QA [Slides] Conversational QA Long QA Reading: Conversational information seeking (Chapters 2,7)
Mon 28. Feb	Paper Presentations II
Wed 2. Mar	Entailment and Fact Checking
	Videos: NLI [Slides] Fact Checking Readings: NLI Automated Fact Checking
Fri 4. Mar	Homework Due	HW2
Mon 7. Mar	Paper Presentations III
Wed 9. Mar	Multimodal QA: Audio, Video
	Videos: Speech [Slides] Images Manchester Multimedia Questions Readings: A Survey on VQA: Datasets and Approaches (Very hard to find things that are good and recent, suggestions welcome!)
Fri 11. Mar	Project Checkpoint	Abstract
Mon 14. Mar	Midterm Review
Wed 16. Mar	Midterm
Mon 28. Mar	Group Reformation, Checkin
	Videos: Course Evaluations
Wed 30. Mar	How to Write a Paper I
	Videos: Why writing well is important How to structure sentences and paragraphs What a good paper looks like How to write an effective abstract Citation mistakes Readings: On Writing Well
Fri 1. Apr	Project Checkpoint	Experiment Plan, Introduction
Mon 4. Apr	How to Write a Paper II
	Videos: Writing with LaTeX Writing for Multiple Audiences How to Review a Paper How to write an effective abstract Taking advantage of virtual presentations Readings: A Beginner's Guide to LaTeX How to Review Conference Submissions
Wed 6. Apr	Evaluation: Leaderboards and IRT
	Videos: History of Standardized Tests IRT IRT for QA Eval QA as Gameshow Readings: Recent Developments in Item Response Theory with Implications for Teacher Certification Introduction to IRT for NLP
Mon 11. Apr	Other QA Formats: MC, Crosswords
	Videos: Crosswords Multiple Choice Readings: Dr. Fill
Wed 13. Apr	Project Conferences
Fri 15. Apr	Project Checkpoint	Baselines, Related Work
Mon 18. Apr	Graphics and Figures
	Reading: Plotnine Videos: The Grammar of Graphics Introducing Plotnine Napoleon in Russia How not to visualize something
Wed 20. Apr	Explainable, Cooperative, and Adversarial QA
	Reading: Toward a Rigorous Science of Interpretable Machine Learning Mythos of Interpretability Videos: What makes for an explanation QA Explanation Cooperative QA Adversarial QA
Mon 25. Apr	Tabular QA (not flipped)
	Reading: Compositional Semantic Parsing on Semi-Structured Tables SEQ2SQL: GENERATING STRUCTURED QUERIES FROM NATURAL LANGUAGE USING REINFORCEMENT LEARNING TAPAS: Weakly Supervised Table Parsing via Pre-training Slides: Tabular QA
Wed 27. Apr	Fairness in Question Answering
	Reading: AI Predictions Addressing Fairness, Bias, and Appropriate Use of Artificial Intelligence and Machine Learning in Global Health On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? QA Demographics (Optional) UnQovering (Optional) Videos: AI Fairness QA Fairness AI and Society
Fri 29. Apr	Project Checkpoint	Conforming Draft
Mon 2. May	Ask Me Anything: No Reading, No Videos
Wed 4. May	Paper Workshop
Fri 6. May	Project Checkpoint	Optional Feedback
Mon 9. May	Poster Session
Mon 16. May	Project Checkpoint	Final Submission

Page by Jordan Boyd-Graber.