Schedule

Plan Materials Resources Assignments
Mar 29
  1. Lecture followed by open discussion
  1. Video: Course overview [slides]
  2. Notebook: Course set-up
  3. Notebook: Jupyter notebook tutorial
  4. Notebook: NumPy tutorial
  5. Notebook: PyTorch tutorial
  1. Levesque 2013
  2. Manning 2015
  3. Potts 2019
  4. Video: The challenge and promise of artificial intelligence
  5. Podcast: The ELIZA effect (99% Invisible)
  1. HW1 and bakeoff 1: due Apr  12, 4:30 pm Pacific [overview video]
  2. Quiz on course policies: due Apr  12, 4:30 pm Pacific
  3. Quiz 1: due Apr  12, 4:30 pm Pacific
Mar 31
  1. HW1 overview followed by open discussion
  1. Video: High-level goals and guiding hypotheses [slides]
  2. Video: Matrix designs [slides]
  3. Video: Vector comparison [slides]
  4. Video: Basic reweighting [slides]
  5. Notebook: Designs, distances, basic reweighting
  6. Video: Dimensionality reduction [slides]
  7. Notebook: Dimensionality reduction and representation learning
  8. Video: Retrofitting [slides]
  9. Notebook: Retrofitting
  10. Video: Static representations from contextual models [slides]
  11. Notebook: Static representations from contextual models
  1. Turney and Pantel 2010
  2. Smith 2019
  3. Mikolov et al. 2013
  4. Pennington et al. 2014
  5. Faruqui et al. 2015
  6. Bommasani et al. 2020
Apr 5
  1. Free work session with teaching team support
Apr 7
  1. Free work session with teaching team support
Apr 12
  1. HW2 overview followed by open discussion
  1. Video: Overview of supervised sentiment analysis [slides]
  2. Video: General practical tips [slides]
  3. Video: Stanford Sentiment Treebank [slides]
  4. Notebook: Overview of the Stanford Sentiment Treebank
  5. Video: DynaSent [slides]
  6. Video: sst.py [slides]
  7. Video: Hyperparameter search and classifier comparison [slides]
  8. Video: Feature representation [slides]
  9. Notebook: Hand-built feature functions
  10. Video: RNN classifiers [slides]
  11. Notebook: Dense feature representations and neural networks
  1. Pang and Lee 2008
  2. Socher et al. 2013
  3. Goldberg 2015
  4. Tutorial videos on supervised learning
  5. Stanford AI Lab Deep Learning Tutorial
  1. HW2 and bakeoff 2: due Apr 21, 4:30 pm Pacific [overview video]
  2. Quiz 2: due Apr 21, 4:30 pm Pacific
Apr 14
  1. Free work session with teaching team support
Apr 19
  1. Open discussion
  1. Video: Overview of contextual representation models [slides]
  2. Video: Transformers [slides]
  3. Video: BERT [slides]
  4. Video: RoBERTa [slides]
  5. Video: ELECTRA [slides]
  6. Video: Practical fine-tuning [slides]
  7. Notebook: Fine-tuning large language models
  1. McCann et al. 2017
  2. Peters et al. 2018
  3. Vaswani et al. 2017
  4. Devlin et al. 2018
  5. Liu et al. 2019
  6. Yang, Dai, et al. 2019
  7. Clark et al. 2019
Apr 21
  1. HW3 overview followed by open discussion
  1. Video: Overview of grounded language understanding [slides]
  2. Video: Speakers [slides]
  3. Video: Listeners [slides]
  4. Video: Varieties of contextual grounding [slides]
  5. Video: The Rational Speech Acts model [slides]
  6. Video: Neural RSA [slides]
  7. Notebook: Pragmatic color describers
  1. Lewis et al. 2017
  2. Golland et al. 2010
  3. Andreas and Klein 2016
  4. Monroe et al. 2017
  5. Tellex, Knepper, et al. 2014
  6. Vogel et al. 2014
  1. HW3 and bakeoff 3: due May 3, 4:30 pm Pacific [overview video]
  2. Quiz 3: due May 3, 4:30 pm Pacific
Apr 26
  1. Free work session with teaching team support
Apr 28
  1. Open discussion
  1. Video: Overview of Natural Language Inference [slides]
  2. Video: SNLI, MultiNLI, and Adversarial NLI [slides]
  3. Notebook: Tasks and datasets
  4. Video: Dataset artifacts and adversarial testing [slides]
  5. Video: Modeling strategies [slides]
  6. Notebook: NLI models
  7. Video: Attention [slides]
  1. Dagan et al. 2006
  2. MacCartney and Manning 2008
  3. Bowman et al. 2015a
  4. Bowman et al. 2015b
  5. Rocktäschel et al. 2015
  6. Williams et al. 2018
  7. Nie et al. 2019
  8. Jia and Liang 2017
  9. Glockner et al. 2018
  10. Liu et al. 2019
  11. Naik et al. 2019
May 3
  1. Lit review overview followed by open discussion
  1. Video: Overview of NLU and Information Retrieval [slides]
  2. Video: Classical IR [slides]
  3. Video: Neural IR, part 1 [slides]
  4. Video: Neural IR, part 2 [slides]
  5. Video: Neural IR, part 3 [slides]
  1. Lit review: due May 12, 4:30 pm Pacific
  2. Quiz 4: due May 19, 4:30 pm Pacific
May 5
  1. Free work session with teaching team support
May 10
  1. Open discussion
  1. Video: Overview of relation extraction with distant supervision [slides]
  2. Video: Data resources [slides]
  3. Video: Problem formulation [slides]
  4. Video: Evaluation [slides]
  5. Video: Simple baselines [slides]
  6. Notebook: Relation extraction with distant supervision: Task definition
  7. Video: Directions to explore [slides]
  8. Notebook: Relation extraction with distant supervision: Experiments
  1. Snow et al. 2005
  2. Mintz et al. 2009
May 12
  1. Free work session with teaching team support
  1. Experimental protocol: due May 24, 4:30 pm Pacific
May 17
  1. Free work session with teaching team support
  1. Video: Overview of methods and metrics [slides]
  2. Video: Classifier metrics [slides]
  3. Video: Natural language generation metrics [slides]
  4. Notebook: Evaluation metrics
  5. Video: Data organization [slides]
  6. Video: Model evaluation [slides]
  7. Notebook: Evaluation methods
  1. Resnik and Lin 2010
  2. Smith 2011, Appendix B
May 19
  1. Free work session with teaching team support
  1. Video: Overview of analysis methods in NLP [slides]
  2. Video: Adversarial testing [slides]
  3. Video: Adversarial training (and testing) [slides]
  4. Video: Probing [slides]
  5. Video: Feature attribution [slides]
May 24
  1. Open discussion
  1. Presenting your work: Your final papers [slides]
  2. Writing NLP papers [slides]
  3. NLP conference submissions [slides]
  4. Giving talks [slides]
  1. Jason Eisner's Advice for Research Students
  2. Stuart Shieber on reporting research results
  3. David Goss on math style
  4. Novelist Cormac McCarthy’s tips on how to write a great science paper
  5. Geoff Pullum's Five Golden Rules (well, actually six) for giving academic presentations
  6. Patrick Blackburn: How to give a good talk
  1. Final paper: due June 4, 11:59 pm, anywhere in the world
May 26
  1. Free work session with teaching team support
May 31
  1. Memorial Day (no class)
Jun 2
  1. Free work session with teaching team support