B.A. (Mod.) in Computer Science and Language
CLCS is responsible for the linguistics components of the degree, which include the following:
- Junior Freshman
- Senior Freshman
- LI2034 Syntax and Semantics (S1, 5 ECTS)
- LI2036 Computational Morphology and Statistics (S1, 5 ECTS)
- LI2035 Speech Science and Phonetics (S2, 5 ECTS)
- Junior Sophister
- LI2303 Language Learning (S1, 5 ECTS)
- LI2307 Aspects of Written Language (S1, 5 ECTS)
- LI2301 Aspects of Vocabulary (S2, 5 ECTS)
- Senior Sophister
- LI4031 Speech Analysis and Synthesis (S1, 5 ECTS)
- LI4032 Computational Linguistics (S2, 5 ECTS)
- LI4034 Second Language Acquisition (Option, S1 & S2, 10 ECTS)
- LI4036 Fourth Year Project - Linguistics (Option, S1 & S2 10 ECTS) (PDF 148K)
LI036 Fourth Year Project - Linguistics
Some project suggestions:
Rule-based machine Translation for Irish-English language pair.
This project would involve developing transfer grammar rules for Irish-to-English or English-to-Irish machine translation using Apertium - an open source rule based machine translation system (RBMS) hich has been used for several other language pairs. See http://www.apertium.org/index.eng.html#translation and http://wiki.apertium.org/wiki/Main_Page for more details. In this project you would be building on work carried out in a previous final year project for the Irish-English pair using the Apertium system (Shaw 2013). If you are interested in this project contat Elaine Uí Dhonnachadha (firstname.lastname@example.org) for further details.
Query for Interface for Corpus of Spoken Irish: Implement Phonological Query Interface for Corpus of Spoken Irish (comhra.ie) using Glossa an open source system (or a similar system). Glossa is implemented using MySQL and PHP. See http://www.hf.uio.no/iln/tjenester/kunnskap/sprak/glossa/LREC-glossa_2008.pdf and http://www.hf.uio.no/iln/english/about/organization/text-laboratory/services/glossa.html. If you are interested ihn this project contact Elaine Uí Dhonnachadha (email@example.com)
Morphological Analysis of Irish Child Language Acquisition Data in CHILDES
CHILDES is a system of standards and tools which enables researchers to share and analyse language transcripts (e.g. language acquisition, language disorders, etc.) In this project you would be asked to develop an online interface where users can generate the morphological anaysis tier of Irish language transcripts in CHAT format. The system will use a part-of-speech tagger for Irish to analyse the input transcript. The output will need to be converted to the required CHAT format in order to work with the CLAN tools. For information on CHILDES/CHAT/CLAN see http://childes.psy.emu.edu/ and for an example of the required output see %mor line in this online transcripts http://childes.psy.cmu.edu/browser/index.php?url=Eng-NA-MOR/Brent/m2/m2-1504.cha. If you are interested in this project contact Elaine Uí Dhonnchadha (firstname.lastname@example.org) for further details.