This part of the course serves as the introduction. For outsiders, SEM1A5 is a first year undergraduate module in Natural Language Processing. Students taking this module will typically have followed an introductory programming language module and an introductory module on Artificial Intelligence.
This lecture to accompany this section covers some introductory material, particular the meaning of the title, some history, current applications, a review of the state-of-the-art in Natural Language Processing and research directions. These notes take some of the topics further, suggesting directions for students to study further. The tutorial notes are exercises to be completed in time for a small group tutorials.
In more detail, this part includes:
- What's in a name?
- The name of the course suggests a particular view of the material to be covered. This is contrasted with similar course titles to show some different approaches to studying natural language.
- What is natural language and what is linguistics?
- This module is restricted to the study of natural language. Linguistics is the study of language, but if you hoped this course would help you to "talk proper", you are about to be disillusioned. Linguistics is about description, not prescription.
- A brief history of Natural Language Processing
- NLP started when the computer was demobbed after the Second World War. Since then, it has been used in a variety of roles, starting with machine translation to help fight the Cold War to the present, when it is used for tools to aid multilingual communication in international communities.
- The state-of-the-art
- This is a brief description of the main techniques and methods used in NLP. These are expanded upon in the rest of the course.
- Research topics
- Despite many years of world-wide research effort, there remain large problems that remain to be solved. This section looks at some of the current trends in research that look promising.