Founded in 2006, LT³ is a research group at Ghent University's Department of Translation, Interpreting and Communication which conducts fundamental and applied research on different aspects of Natural Language Processing (NLP) from a corpus-based inductive perspective.
The team has extensive expertise in the use of machine learning for a wide range of language technology problems. Based on the conviction that shallow representations based on lexical information are not sufficient to model text understanding, the team heavily invested in deep syntactic and semantic modeling of text and the integration of this knowledge in end-user applications.
LT³ is currently very active in the following areas:
- Language technology: text normalisation, coreference resolution, cross-lingual transfer models, detection of events, sentiment, irony, arguments and emotion in (financial) news data and social media
- Translation technology: machine translation, post-editing, human-computer interaction, translation quality and translation difficulty assessment
- Terminology: automatic (multilingual) terminology extraction and terminology management
- Language and translation technology for educational applications: automatic writing evaluation and readability assessment, vocabulary and example selection for second language acquisition, machine translation for language learning.
- Digital Humanities: digital text analysis tools for research in the humanities and social sciences
The team teaches several modules at bachelor and master level. Both the CALM (Computer-Assisted Language Mediation) postgraduate and the European Masters in Technology for Translation and Interpreting (EM-TTI) are founded on the established expertise in language and translation technology within the research group.