Introduction to Natural Language Processing

Semester A, 2018-2019

Instructors: Prof. Yoav Goldberg and Prof. Ido Dagan
Emails: yogo,dagan /
Offices: Building 216
Office Hours: By email appointment


Online Discussion Forums

Managed via Piazza


  1. Assignment 1, deadline Nov 19, Midnight. [can submit up to Thursday, Nov 22, with 10 points penalty]

  2. Assignment 2, deadline Dec 3, Midnight.

  3. Assignment 3, deadline Dec 17, Midnight.

  4. Assignment 4, deadline Jan 3, Midnight.

Machine Learning Reading Material

Students who do not take the Machine Learning course can read the first 3 chapters of the following Book. You are encouraged to read chapters 4 and 5 also (as well as the rest of the book, but this is not needed for our class).


  1. Intro to Natural Language Processing, and discussion of sentence-boundary detection problem. intro (Ido) || intro (Yoav)

  2. PP-attachment and simple probabilistic modeling (slides)
    Discriminative Training (slides).
    Parts of Speech (slides) (up to open vs. closed class).

  3. Parts of speech slides (continuing from last time)
    Tagging with HMMs slides

  4. Discriminative tagging (MEMM) slides
    Sequence Segmentation. slides

  5. Syntax, Grammars, Constituents and Dependencies. slides

  6. Distributional Similarity. slides

  7. More Distributional Similarity (embeddings). slides

  8. Information and Relation Extraction slides
    Representing Semantic Relationships slides

  9. Parsing Algorithms slides
    Mike Collins' PCFG and CKY notes

  10. Semantics (+ some more IE) ppt pdf

  11. Unsupervised Learning and LDA. slides

  12. Coreference Resolution. slides

  13. Biases in Text, Ethics. main slides, "making a racist AI" .html,.ipynb, Text is predictive of demographics slides (Yanai), Bias In Text slides, Ethics slides (Yulia)