Link
BM1: Advanced NLP

This site uses Just the Docs, a documentation theme for Jekyll.

Search

University of Potsdam, MSc CogSys, Winter 2019/2020

BM1 - Advanced Natural Language Processing

Instructor Prof. Dr. David Schlangen
Email david.schlangen@uni-potsdam.de
Office Hours Thursdays, 1-2pm
Class Hours Wednesdays, 4-6pm; Thursdays, 10-12
Class Room 2.14.2.22; 2.14.0.09
Class Website on github; on moodle

Course Description

This class is the graduate-level introduction to natural language processing, a first-year class in the MSc Cognitive Systems. The purpose of this class is to introduce the important concepts, models and methods used in natural language processing (NLP). After the successful completion of this course, students should be able to (i) read and understand the scientific literature in the area of computational linguistics and (ii) start implementing their own NLP projects.

We will cover the following topics:

  • statistical models of language
  • part of speech tagging (HMMs)
  • syntactic parsing (PCFGs, others?)
  • semantics
  • classification
  • deep learning for NLP

and more

Background Readings

I will mostly follow these textbooks:

  • Dan Jurafsky & James H. Martin, Speech and Language Processing, 3rd edition (draft available online. Rerences to this are written as JM-3.i.k in the Schedule, with i being the chapter.
  • Jacob Eisenstein, Introduction to Natural Language Processing, MIT Press (draft available online). Referred to as E.chapter.

Also useful as background reading:

  • Yoav Goldberg, Neural Network Methods for Natural Language Processing, Morgan & Claypoole, 2017 (If you are on the UP network, you can download this from here.)

Requirements

  • active participation
  • completion of the assignments: at least 5 (out of 6) assignments must be turned in (via moodle). No late submissions!

Grading Policy

Passing the course

To be admitted to the module exam, you need to pass the course. For this, we will grade the best two assignments out of each half of the semester (i.e., the best 2 from the first 3 + the best 2 from the second 3). At least 250 points in total (out of 400) in these 4 assignments are needed to pass the course.

Module grade

The grade will be based on a collaborative final project, to be completed during the semester break. There are four graded deliverables for this project:

  1. a planning paper (individual)
  2. a project presentation (group)
  3. the implemented project (group)
  4. a project report (individual)

The grade will be composed equally from these four parts. Details will be discussed in class.