Department of Computer Science and Technology

Course pages 2017–18

Overview of Natural Language Processing

Assessment is by coursework as follows:

A practical is performed where a corpus of movie reviews is given, and students write code that detects the sentiment of each text as positive or negative. In the first task, students build two commonly used baselines (which should be comparable across students), one based on a sentiment lexicon, and another based on a reimplementation of a classic machine learning approach. In the second task (extension implementation), students improve over the baselines using document embeddings and perform an error analysis on the strengths and weaknesses of the approach.

Detailed instructions can be found here (v1.2).

Slides for the first task can be found here and here. Slides for the second task can be found here.

Practical sessions: 8 November, 15 November and 29 November, 9--11am, SW02.

Assessment is by two reports on the practical (on paper to Student admin):

  • First task report (10%, ticked, up to 1,000 words, excluding references) due on Friday 17 November 2017 at 12:00 noon.
  • Second task report (90%, 4,000 words, excluding references) due on Wednesday 17 January 2018 at 12:00 noon.

Your reports should include a word count and a pointer to your working code on the Mphil machines (your account).