- 08/23/2017: Welcome to the Natural Language Processing class!
- 08/23/2017: Slides and readings posted -- please follow every week’s.
- 08/29/2017: Summary writing HW1 posted+emailed.
- 08/30/2017: TA = Yixin Nie (email@example.com). His office hours are Wed 2.30-3.30pm in SN208, which is the 2nd floor reading room (see details above)!
- 09/17/2017: Summary writing HW2 posted+emailed.
- 09/21/2017: Coding HW1 (on word embedding training + visualization + evaluation) released — see details in email and our TA Yixin's link!
This course will be based on the artificial intelligence and machine learning field of natural language processing (NLP, or computational linguistics), and its important multimodal connections to computer vision and robotics. First we will cover traditional topics of NLP such as tagging, parsing, coreference resolution, sentiment analysis, summarization, question-answering, and translation. Then, we will 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.
Topics (tentative, based on time)
- 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
- Several interesting machine and deep learning models all along the way, e.g., deep+structured models, interpretable models, adversarial models, reward-based models (reinforcement learning)
Since this is a graduate research-level class, some machine learning and coding experience is expected (see references below). Previous courses in probability and linear algebra are also highly recommended.
Grading will consist of:
Details in first class intro lecture slides. There will not be any exams. All submissions should be emailed to: firstname.lastname@example.org
- project presentations and write-ups (midterm = 15% and final = 25%; total = 40%)
- homework assignments (30%)
- paper presentations (10%)
- paper written summaries (10%)
- class participation, discussion, and brainstorming (10%)
Students are allowed 3 free late days for assignments over the semester. After that, late assignments will be accepted with a 10-20% reduction in value per day late.
Homeworks and paper summaries have to be written and submitted individually. Projects are encouraged to be done in pairs (but individual projects are fine too, e.g., if it relates to your current research), with clearly outlined contributions from each team member.
|Date||Topic (& slides) || Readings ||Discussion Leaders||Todo's (Assignments, Homeworks)|
|Aug 23||Intro to the Course, Language Modeling (N-gram, RNNs, etc.) (slides) || SLP3 Chapters 1-4, 8; SLP2 Chapters 1-4 || Mohit || Summary due Sep05 midnight for SLP3 Sections 4.5, 8.4, 8.5
|Aug 30||Travel (make-up sessions emailed to you) || -- || -- ||-
|Sep 06|| Word/Sentence Embeddings, Text Classification (slides) || SLP3 Chapters 6, 15, 16 || Mohit ||-
|Sep 13|| Part-of-Speech Tagging, NER, Sequence Labeling, Coreference Resolution (slides) || SLP3 Chapters 9, 10, 24; SLP2 Chapters 5, 6, 21 || Mohit ||Summary due Sep24 midnight for SLP3 Sections 9.5, 10.5
|Sep 20|| Syntactic Parsing || SLP3 Chapters 11, 12, 13, 14; SLP2 Chapters 12, 13, 14 || Mohit || Coding HW1 (Word Embedding Training, Visualization, Evaluation) -- due Oct5
|Sep 27|| SRL, Semantic Parsing, Compositional Semantics 1 || SLP3 Chapters 22; SLP2 Chapters 18, 19, 20 || Mohit ||-
|Oct 04|| Claire Cardie (Cornell) Talk, Compositional Semantics 2 || -- || Mohit ||-
|Oct 11|| Question Answering || -- || Mohit ||-
|Oct 18|| Midterm Project Presentations || -- || All Students ||-
|Oct 25|| Document Summarization || -- || Mohit || Midterm Write-ups Due
|Nov 01|| Machine Translation || -- || Mohit ||-
|Nov 08|| Dialogue Models || -- || Mohit ||-
|Nov 15|| Language+Vision (Image/Video Captioning, Visual Q&A) || -- || Mohit ||-
|Nov 22|| Language+Robotics 1 || -- || Mohit ||-
|Nov 29|| Language+Robotics 2 || -- || Mohit ||-
|Dec 06|| Final Project Presentations || -- || All Students ||-
|Dec 12|| 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.