- 08/12/2020: Welcome to the Natural Language Processing class (for graduate students and senior/advanced undergraduates)!
- 08/19/2020: Slides posted weekly; please check links below.
- 08/26/2020: Summary writing homeworks posted+emailed regularly.
- 09/11/2020: Coding HW1 (on word embedding training + visualization + evaluation) released — see details in email.
- 09/16/2020: Midterm project presentation details emailed.
- 10/01/2020: Midterm reports due to Oct10.
- 10/16/2020: Coding HW2 (on Sequence-to-Label Learning, Entailment Recognition) released — see details in email (due Oct30).
This course will be based on the artificial intelligence, machine learning, and linguistics field of natural language processing (NLP, or computational linguistics), to allow building automatic models that can analyze, understand, and generate text. We will cover important traditional topics of NLP such as tagging, parsing, coreference resolution, sentiment analysis, summarization, question-answering, and translation. We will also cover more recent topics of multimodal, grounded, and embodied semantics (i.e., language with vision and speech, for robotics), language generation and dialogue, and interpretable deep learning, etc.
- Language Modeling
- Part-of-speech Tagging
- Syntactic Parsing: Constituent, Dependency, CCG, others
- Coreference Resolution
- Distributional Semantics: PMI, neural, CCA
- Compositional Semantics: Logical-form, Semantic Parsing, Vector-form, neural (RNNs/CNNs)
- Question Answering: Factoid-based, Passage-based
- Sentiment Analysis
- Document Summarization
- Machine Translation
- Dialogue Models
- Language and Vision: Image Captioning, Video Captioning, Visual Question Answering
- Language and Robotics: Instructions for Navigation, Manipulation, Skill Learning; Human-Robot Interaction
- Models: Deep+structured, interpretable, adversarial, reward-based (reinforcement learning), etc.
- Ethics and Bias in NLP/ML Models
- How to Write and Review Research Papers
Students not meeting these requirements must receive the explicit permission of the instructor to remain in this course.
- COMP 562 (Introduction to Machine Learning)
- A reasonable knowledge of Python programming language (preferably Pytorch/Tensorflow style libraries) and Linux program development environment.
Grading will (tentatively) consist of:
All submissions should be emailed to: firstname.lastname@example.org.
- Written homework and programming assignments (20\%),
- Midterm Project write-up and presentation (20\%)
- Final Project write-up and presentation (30\%)
- Paper presentations and written summaries (20\%)
- Class brainstorming and participation (10\%).
Students are allowed 3 free late days for assignments over the semester. After that, late assignments will be accepted with a 25\% reduction in value per day late.
Schedule (tentative; slides coming soon)|
|Date||Topic (& slides) || Readings ||Discussion Leaders||Todo's (Assignments, Homeworks)|
|Aug 12||Intro to the Course, Language Modeling (N-gram, RNNs, etc.) (slides) || SLP3 Chapters 1, 2, 3, 7, 9; SLP2 Chapters 1-4 || Mohit || -
|Aug 19|| Word/Sentence Embeddings, Text Classification (slides) || SLP3 Chapters 4, 5, 6 || Mohit || Chapter summary due Aug26 for 8.4.5, 8.5 (Viterbi and MEMMs)
|Aug 26|| Part-of-Speech Tagging, NER, Sequence Labeling, Coreference Resolution (slides) || SLP3 Chapters 8, 9, 10, 22; SLP2 Chapters 5, 6, 21 || Mohit || Chapter summary due Sep2 for 13.2, 14.2 (CKY algo)
|Sep 02|| Syntactic Parsing (slides) || SLP3 Chapters 12, 13, 14, 15; SLP2 Chapters 12, 13, 14, 15 || Mohit || Chapter summary due Sep9 for 20.6.1, 20.6.2 (SRL models)
|Sep 09|| Project Brainstorming+Feedback || || Mohit || Coding HW1 (Word Embedding Training, Visualization, Evaluation) -- due Sep23 midnight
|Sep 16|| SRL, Semantic Parsing, Compositional Semantics 1 (slides) || SLP3 Chapters 16, 17, 20; SLP2 Chapters 18, 19, 20 || Mohit || Short project description (based on Sep9 feedback) due Sep21
|Sep 23|| Semantic Parsing 2, Question Answering (slides) || SLP3 Chapters 25; SLP2 Chapters 23 || Mohit ||-
|Sep 30|| Midterm Project Presentations || -- || All Students ||Midterm Write-ups Due Oct10
|Oct 07|| Document Summarization, Machine Translation (slides) || SLP3 Chapters 11, 24; SLP2 Chapters 23, 25 || Mohit (+guest talk by Ram) || Chapter summary due Oct14 for Sec5.2 EM algo for IBM models (Mike Collins' pdf)
|Oct 14|| Machine Translation 2 (Neural), Dialogue Models (slides) || SLP3 Chapters 11, 26; SLP2 Chapters 24, 25 || Mohit || Coding HW2 (Sequence-to-Label Learning, Entailment Recognition) -- due Oct30 midnight
|Oct 21|| Language+Vision (slides) || -- || Mohit + guest talks ||-
|Oct 28|| L+V part2; Language+Robotics (slides) || -- || Mohit ||-
|Nov 04|| Ethics+Bias in NLP/ML; How to Write+Review Research Papers (slides) || -- || Mohit ||-
|Nov 11|| Final Project Presentations (last class as per new UNC calendar) || -- || All Students ||-
|Nov 21|| Final Project Write-ups Due || -- || All Students || Project Write-ups Due
The professor reserves the right to make changes to the syllabus, including project due dates. These changes will be announced as early as possible.