Schedule

Note: Future schedule is subject to minor change. Please refer to Gradescope for HW due date.

Introduction

• Week 1 (Sep 8). Overview: NLP tasks and challenges, basic ML

  • notes, slides 1, slides 2

Representation of text

• Week 2 (Sep 15). Text classification: bag-of-words, naive Bayes models, logistic regression

  • notes, slides

• Week 3 (Sep 22). Distributed representation: vector space models, Brown clusters, neural word embeddings

  • notes, slides

Predicting sequences

• Week 4 (Sep 29). Language models: n-gram LM, neural LM, perplexity

  • notes, slides

• Week 5 (Oct 6). Sequence labeling: log-linear models, decoding, POS tagging

  • notes, slides

• Week 6 (Oct 13). Hidden Markov models: HMM, EM

  • J&M HMM, Collins EM, slides

• Week 7 (Oct 20). Midterm.

  • topics

Predicting trees

• Week 8 (Oct 27). Context-free parsing: PCFG, CYK, neural parser

  • Collins PCFG, Eisner Inside-Outside, slides

• Week 9 (Nov 3). Semantic parsing: logical semantics, learning from logical forms / denotations

  • E Ch12, Liang 16, slides

Deep learning for NLP

• Week 10 (Nov 10). Neural sequence modeling: seq2seq, attention, copy mechanism, text generation

  • slides, D2L 9.7, 9.8, 10

• Week 11 (Nov 17). Representation learning: transformers, contextualized word embedding, pre-training and fine-tuning, autoencoders

  • slides

  • Representation Learning: A Review and New Perspectives

Beyond text

• Week 12 (Nov 24). Language grounding: language+vision/robotics, pragmatics, RL agents

  • slides

Conclusion

• Week 13 (Dec 1). Guest lecture on natural language interface by Victorial Lin

  • slides

  • Advice on writing and presentation

• Week 14 (Dec 8). Project presentations