Natural Language and Information Processing Research Group

Graduate courses in computational linguistics and language technologies

The NLIP group offer a range of modules in the Masters in Advanced Computer Science (ACS), allowing students to specialise in language processing, or a mixture of language and speech. We also welcome PhD applications from students with some previous experience of NLIP topics. These options are discussed in more detail on this page.

Language and speech on the ACS MPhil

The following modules on language processing and taught by members of the NLIP group (in some cases in conjunction with staff from the Engineering department).

• Introduction to Natural Language Processing (Copestake and Clark) This module provide a brief introduction to linguistics for computer scientists and then goes on to describe some of the core tasks in language processing. We expect most students interested in language processing to take this, unless they have covered the material in a previous course.
• Machine Learning for Language Processing (Briscoe and Clark)
  An introduction to machine learning with specific application to tasks such as document topic classification, spam email filtering, and named entity and event recognition for textual information extraction. The techniques introduced have applications outside language processing and might therefore be of interest to students interested in other topics in AI.
• Statistical Machine Translation (Byrne and Clark)
  An in-depth introduction to statistical machine translation (MT), the dominant approach to providing large-scale, robust translation applicable to many language pairs (and the approach currently used by Google).
• Syntax and Semantics of Natural Language (Briscoe and Clark)
  Looks at the formal description of language using Categorial Syntax and Montague Semantics and the implementation of practical parsers using these techniques. This module might be of interest to students who are also taking modules in theoretical computer science or in automated reasoning.
• Language and Concepts (Copestake)
  The notion of a concept is crucial to the way that we think about representation of language and human cognition. Concepts are relevant to AI and NLP/computational linguistics as well as other areas of Computer Science which are concerned with modelling the real world in a way which is comprehensible to humans, including semantic web technology. The aim of this course is to start from a computational perspective but to provide an overview of the interdisciplinary issues involved in the study of concepts, including ideas from linguistics, cognitive science, philosophy and neuroscience.
• Word Meaning and Discourse Understanding (Teufel)
  Models of word meaning which can be derived from corpora and approaches to representing the relationship between sentences and other text units. It should be of interest to students who are interested in knowledge representation and who want to learn about the latest computational linguistics techniques.

Note also the Spoken Language Processing module which is taught by staff from the Engineering department. Detailed advice on module selection can be obtained from the course advisor for students accepted on the ACS.

The ACS MPhil can be taken either as a predominantly taught course (Option A) or with a research project which is of equal weight to the taught modules (Option B). See the ACS admissions page for further details. We would prefer students to take Option B if they wish to concentrate on language processing, since it is essentially an experimental subject. The ACS is mainly designed for students who wish to go on to take a PhD, and gaining experience of research via the project is an important aspect of this. Option B students concentrating on language processing will be assigned a project supervisor from the NLIP group. A list of some of the projects which Masters students have taken in previous years (on the previous CSTIT Masters course) can be found here. Students doing Option A will generally be taking a smaller number of language and speech modules to complement their choice of other topics.

PhD applications to the NLIP group

In general we would expect student who wish to start a PhD without doing the ACS to have taken some courses in language processing at undergraduate or masters level and to have done a short research project in the area. The application requirements for the PhD include a research proposal: applicants are welcome to contact the member of the NLIP staff with interests closest to their own to discuss this. See individual staff pages (Briscoe, Clark, Copestake, Teufel and Korhonen), the pages for group research projects and current PhD students' pages. We are also happy to advise on whether applicants should apply directly for the PhD or should take the ACS first.

These slides give a very brief overview of some recent research topics by PhD students in the NLIP group.