robot reading TOPICS IN NATURAL LANGUAGE PROCESSING (SEMESTER 2, 2018)


For the 2017 class website, click here.


INTRODUCTION TO THE COURSE

Lecturer: Shay Cohen
Teaching Assistant: Nikos Papasarantopoulos
Time and Location: Monday 11am-12pm, 2.12 Appleton Tower; Thursday 11am-12pm, Lecture Theatre 2, 7 Bristo Square (semester 2)
Office Hours: Set an appointment.

Welcome! Natural language processing is an application area in computer science, heavily supported by the industry with new applications emerging on a constant basis. The goal of this course is to give a different angle and look into natural language processing. We will explore basic concepts in computer science, machine learning, and statistics that make natural language processing such a rich area of research. You will learn how to use generic methods for application to specific problems you need to address in order to make use of natural language. As such, we will take a method-oriented view of NLP instead of an application-oriented one.

Topics we will discuss include: basic probability and statistics used in NLP, structured prediction with log-linear models, Bayesian inference, finite state transducers, context-free grammars and other constructs, latent-variable modeling and deep learning and representation learning.

Hopefully, after taking the class, when using a generic NLP tool such as a part-of-speech tagger or a syntactic parser, you will be able to hypothesize how the tool generally works under the hood and why. This class can also assist you later in research in natural language processing, should you choose to pursue a PhD degree in the area.

KNOWLEDGE REQUIRED

You should probably feel comfortable with basic concepts from probability and statistics. There will be an introduction for the basic ideas in statistics and probability we will use, such as conditional independence assumptions, parametric modeling and statistical estimation. You should also be familiar with some of the basic concepts in NLP, as evidenced by having taken Foundations of Natural Language Processing or Advanced Natural Language Processing.

SCHEDULE

To see a preliminary schedule and topics to be covered, click here.

DISCUSSION FORUM

There is a discussion forum for the class. It can be accessed here. Please make use of it! The forum will be monitored by the instructor, and you are urged to use the discussion site to ask any questions about the class (regarding the material or organisation).

BACKGROUND MATERIAL

There are no official textbooks for the course, but you might want to take a look at

Noah Smith (2011), Linguistic Structure Prediction, Synthesis Lectures on Human Language Technologies, Morgan and Claypool

to get a general feeling of some of the topics we will touch on.

Since the class takes place in the style of a seminar, there will be papers that students are required to present. The papers will be selected in the beginning of the semester.

ASSESSMENT

New: (1) Information and advice regarding the course requirements. (2) Topic list.

Oral presentation (20%): students (in small groups perhaps, depending on enrollment) will choose 1-3 papers on a specific topic (topics can be repeated) from a list provided by the instructor. Freedom will be given to students to choose a topic, if they show they are able to grasp the material and present it well.

Brief paper responses (15%): Students will be paired with 1-2 additional papers (from other student's presentations), and will write a short summary on the topic and these papers for all other students to read (400-800 words). This summary will also suggest ideas to further expand the research presented in these papers, or questions that students had during their readings.

Assignment (10%): Students will solve a pencil-and-paper assignment that covers the first part of the lecture. This assignment is aimed at assessing what students learned in the first part of the course.

Essay (55%): This is the final piece of assessment, in which students could choose a potentially new topic (or stick to the old topic of their presentation and the brief paper responses), and create a literature review of this topic, or an essay based for this topic.

For more information about the class, you can see it here on PATH. For more information about assessment, see here.

Deadlines:


Home : Teaching : Courses 

Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB, Scotland, UK
Tel: +44 131 651 5661, Fax: +44 131 651 1426, E-mail: school-office@inf.ed.ac.uk
Please contact our webadmin with any comments or corrections. Logging and Cookies
Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh