Department of Computer Science and Technology

Course pages 2018–19

Advanced topics in machine learning and natural language processing

Principal lecturers: Prof Ted Briscoe, Dr Damon Wischik
Taken by: MPhil ACS, Part III
Code: R250
Hours: 16 (8 2-hours sessions)
Class limit: 32 students
Prerequisites: L90 or L42 or similar, L95 and L101 for some topics

Aims

This course explores current research topics in machine learning and/or their application to natural language processing in sufficient depth that, at the end of the course, participants will be in a position to contribute to research on their chosen topics. Each topic will be introduced with a lecture which, building on the material covered in the prerequisite courses, will make the current research literature accessible. Each lecture will be followed by up to three seminar sessions which will typically be run as a reading group with student presentations on recent papers from the literature followed by a discussion.

Structure

Each student will attend 4 topics and each topic will consist of 4 sessions. Students will be expected to undertake readings for their selected topics.

Students will be required to rank the topics in order of preference by 4 January 2019.

Syllabus

Students choose exactly four topics from the following: (for illustration only; final topics will be announced in Michaelmas Term 2018)

  • learning to rank,
  • active learning,
  • reinforcement learning,
  • autoencoders and generative adversarial networks,
  • integrating distributional and compositional semantics,
  • constructing and evaluating word embeddings,
  • applications of neural networks to NLP

Example topic materials can be found at http://www.cl.cam.ac.uk/teaching/1617/R222/materials.html

Objectives

On completion of this module, students should:

  • be in a strong position to contribute to the research topics covered.
  • understand the fundamental methods (algorithms, data analysis, specific tasks) underlying each topic
  • and be familiar with recent research papers and advances in the field.

Coursework

Each student will give one or two 20-minute presentations on assigned papers. Each topic will typically consist of one preliminary lecture followed by 3 reading and discussion sessions, so that a typical topic can accommodate up to 6 students presenting a paper each, allowing at least 10 minutes general discussion per session.

Each student will be required to write an essay or undertake a short project and write a project report on ONE of their chosen topics, which will consist of a maximum of 5000 words.

Assessment

  • Students will receive one tick worth 5% for attendance at 16 sessions, reading of assigned material, and satisfactory contribution during seminars.
  • Students will receive a second tick worth 5% for a satisfactory presentation of assigned papers.
  • Students will undertake one small project and write an associated report or write an essay addressing a research issue. The project or essay topic must be agreed with the topic and course organisers. The report or essay will not exceed 5000 words and will account for 90% of the module marks.

Recommended reading

To be confirmed.