| CODE | LIN2031 | ||||||
| TITLE | Machine Learning for Natural Language Processing | ||||||
| UM LEVEL | 02 - Years 2, 3 in Modular Undergraduate Course | ||||||
| MQF LEVEL | 5 | ||||||
| ECTS CREDITS | 6 | ||||||
| DEPARTMENT | Institute of Linguistics and Language Technology | ||||||
| DESCRIPTION | Machine learning is the technique of making computers learn to do something without being told explicitly how to do it. In natural language processing (NLP), many contemporary approaches rely on some form of machine learning techniques to make generalisations about how language is used, often based on large corpora of text and/or datasets. This study-unit introduces the general field of machine learning, with emphasis on how to apply it to natural language. Python machine learning libraries such as scikit-learn will be used to learn how to make practical use of machine learning. In introducing students to this broad field, the unit will also pave the way for deep learning techniques covered in LLT3510. The topics covered will include: - A general introduction to machine learning and the major paradigms in the field; - Evaluation of machine learning outcomes; - Various data preprocessing techniques; - Various machine learning models and algorithms such as decision trees, artificial neural networks, and nearest neighbours algorithms. While all of these are of general applicability in computer science, they will be treated in this unit with a linguistic emphasis, giving students the chance to apply the concepts learned to problems related to NLP. Study-Unit Aims: This unit aims to: - give students a good grounding in machine learning theory and applications; - give students the practical, hands-on knowledge required to apply machine learning algorithms to solve linguistic problems. Learning Outcomes: 1. Knowledge & Understanding: By the end of the study-unit the student will be able to: - identify suitable machine learning techniques to solve various learning problems; - preprocess data in a manner that makes it suitable for machine learning; - evaluate the performance of resulting models. 2. Skills: By the end of the study-unit the student will be able to: - use Python to write a program that applies machine learning to an NLP task; - evaluate the merits and shortcomings of different approaches to machine learning in NLP. Main Text/s and any supplementary readings: Main Texts: - A Course in Machine Learning by Hal Daumé III: http://ciml.info/. - Speech and Language Processing by Dan Jurafsky and James H. Martin: https://web.stanford.edu/~jurafsky/slp3/. |
||||||
| ADDITIONAL NOTES | Pre-requisite qualifications: Familiarity with the Python programming language. | ||||||
| STUDY-UNIT TYPE | Lecture and Practicum | ||||||
| METHOD OF ASSESSMENT |
|
||||||
| LECTURER/S | Marc Tanti |
||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2023/4. It may be subject to change in subsequent years. |
|||||||