Applied Natural Language Processing

Module code: 955G5
Level 7 (Masters)
15 credits in autumn semester
Teaching method: Laboratory, Lecture, Class
Assessment modes: Coursework, Unseen examination

Applied Natural Language Processing concerns the theory and practice of automatic text processing technologies.

In this module, you study core, generic text processing models, such as:

  • tokenisation
  • segmentation
  • stemming
  • lemmatisation
  • part-of-speech tagging
  • named entity recognition
  • phrasal chunking
  • dependency parsing.

You also cover related problems and application areas, such as:

  • document classification
  • information retrieval
  • information extraction.

You gain hands-on experience with the practical aspects of this module through weekly laboratory sessions.

As part of this, you make extensive use of the Natural Language Toolkit, which is a collection of natural language processing tools written in the Python programming language.

Module learning outcomes

  • Given a novel scenario in which automatic text analysis could potentially be of value, assess whether there is scope for successful deployment of NLP technology.
  • Design and implement a system involving generic NLP tools that is suited to a particular problem, selecting approaches that are well-suited to the specific scenario under consideration.
  • Formulate a clear verifiable hypothesis that forms the basis of an attempt to successfully deploy NLP technology.
  • Use appropriate experimental methods to reliably determine the effectiveness of an NLP software tool on actual data.