| CODE | LIN3504 | |||||||||
| TITLE | Multilingual Computing | |||||||||
| UM LEVEL | 03 - Years 2, 3, 4 in Modular Undergraduate Course | |||||||||
| MQF LEVEL | 6 | |||||||||
| ECTS CREDITS | 4 | |||||||||
| DEPARTMENT | Institute of Linguistics and Language Technology | |||||||||
| DESCRIPTION | Multilinguality has been the "holy grail" of NLP since its inception. For example, Machine Translation was one of the first NLP/AI applications in the 1950s-60s. With the growth of large repositories of data in many languages, as well as the increased need for multilingual processing in government and private organisations, there is a resurgence of interest in this field, aided by the arrival of data-driven methods. Just like multilingual people, computing systems also need to be multilingual, that is, not only work in any language but also simultaneously with many languages at the same time. Multilingual processing studies the processing of second and third languages, in particular in multilingual texts. The topics covered include multilingual data and representation, automated transliteration, architectures and mechanisms for machine translation, cross-lingual information retrieval, and the evaluation of multilingual systems. Study-unit Aims Given the centrality of multilingual applications in NLP, it is therefore crucial for students to: - gain an understanding of the history of work in this area; - be familiar with the main trends in current research on multilingualism; - be exposed to the most salient computational approaches to multilingual processing and representation. Learning Outcomes 1. Knowledge & Understanding: By the end of the study-unit the student will be able to: - distinguish between different sub-tasks of this field; for example, the difference between cross-language information retrieval and machine translation; - compare and contrast different approaches to multilingual applications, such as machine translation; - assess the merits of various multilingual applications. 2. Skills: By the end of the study-unit the student will be able to: - identify particular areas in which a computational approach to handling multiple languages can help; - evaluate the performance of multilingual systems using automated approaches as well as experimental ones; - design and implement small-scale systems for the translation and handling of data in a limited number of languages. Main Text/s and any supplementary readings - B. J. Dorr, P. W. Jordan and J. W. Benoir (2000). A Survey of current Paradigms in Machine Translation. [Freely available on: http://www.umiacs.umd.edu/~bonnie/ ] - D. Jurafsky & J. H. Martin (2009). Speech and Language Processing. (2nd edition). Indiana: Prentice Hall [Unavailable in UoM Library] - P. Koehn (2010). Statistical Machine Translation. Cambridge: Cambridge University Press [Unavailable in UoM library] - T. Mitchell (1998). Machine learning. McGraw Hill [Available in UoM Library] - Y. Wilks (2009). Machine Translation: its scope and limits. New York: Springer. [Unavailable in the UoM library] |
|||||||||
| STUDY-UNIT TYPE | Lecture and Seminar | |||||||||
| 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 2024/5. It may be subject to change in subsequent years. |
||||||||||