My research project will aim to domain-adapt Machine Translation (MT) technology for the Bioinformatics domain, and to evaluate this technology. As such, large in-domain parallel corpora (English-French) and monolingual comparable corpora will be compiled. Additionally, a detailed analysis of the linguistic features and patterns (e.g., Multiword Expressions MWEs, Lexical Bundles LBs) found in the domain-specific discourse of Bioinformatics, in both French and English, will be performed.
This project aspires to build bridges between the fields of Machine Translation (MT), Translation Studies, and Bioinformatics, thereby providing valuable contribution to each of these fields of research. Knowledge and expertise from other areas of research, such as Natural Language Processing (NLP), Corpus Linguistics, and Contrastive Linguistics, will also be examined through the lens of this collaborative approach.
This project is in collaboration with the European Molecular Biology Laboratory - European Bioinformatics Institute (EMBL-EBI), and is funded by the Open-Oxford-Cambridge AHRC Doctoral Training Partnership (OOC DTP).