Lecturer: Ivan Titov (titov at uva.nl)

Assistants: Sophie Arnoult, Joachim Daiber, Ehsan Khoddam Mohammadi ({s.arnoult | Daiber.Joachim | E.khoddammohammadi}) at gmail.com

All assistants: nlp.uva.2015 at gmail.com

**Short Description**

This class is an introduction to statistical natural language processing (NLP) for graduate students. The goal is to introduce the students to key challenges and foundational methods of NLP. Specifically, we will study syntactic parsing for constituent and dependency representations, look into shallow representations of semantics (semantic role labeling), topic models and distributional semantics methods. Several lectures will cover important NLP applications such as statistical machine translation and summarization. We will also consider some background from machine learning (specifically, discrimantive and generative models of structures, latent variable models and, time permitting, Bayesian modeling methods and representation learning techniques) crucial in modern NLP.

Blackboard will be used for semi-urgent up-to-date information. The only exception are lecture slides and reading recommendations: they will be posted here.
**Reading**

We will use Jurafsky and Martin's "Speech and Language Processing" (Edition 2) as the main text book. Sections / chapters related to specific lectures are listed below.
Optionally, I would suggest to consider the Manning and Schuetze textbook "Statistical Natural Language Processing". Nevertheless, ** much of the material
presented in the lectures ** is not available in any of them.

**Grading **

- Project: 35%
- Assignments: 25%
- Final exam: 40%

**Project**

- Eleven project directions were discussed during the first lecture (see the slides below). You are welcome to propose your project, as long as it fits the constraints discussed in the slides (e.g., relevance to the class and presence of a programming component). In that case we need to confirm that the project will work for the class.
- Each project team should consist of 3 people. We will aim to have at most 4 teams working on the same direction (some exceptions may be possinle).
- This constraint will be enforced on the first-come-first-served basis. So suggest a second choice, in case you are not lucky with the first one.
- We ask you to do this bidding by the end of Friday, October 30. Of course, include names of all the team participants. Email to use:
`nlp.uva.2015 at gmail.com` - See the slides for the suggested work plan.

**Assignments**

Lecture slides will be made downloadable (after each lecture).