I am an Associate Professor at the Computational Linguistics group, Center for Language and Cognition, Faculty of Arts, University of Groningen (The Netherlands). Prior to starting a faculty position, I was a postdoctoral researcher and research fellow at Dublin City University, and before that a PhD student at the Universitat d’Alacant and at the Istituto di Linguistica Computazionale. I coordinated the Abu-MaTran project, which was flagged by the European Commission as a success story and won the best paper award at MT Summit 2019 for research on post-editese.

My research is in the area of Machine Translation (MT). My main research interests include the application of MT to literary texts, MT for under-resourced languages and the computational analysis of translations produced by machines and humans. My current (and recent) work includes:

  • Enriching parallel corpora for low-resourced European languages (e.g. translation direction) and evaluating such corpora both automatically (by building MT systems) and manually, in the MaCoCu project.
  • Building literary-adapted MT systems, working with professional human translators to explore the usage of such systems for assistance, and testing the reception of such translations with readers.
  • Analysing quantitatively the characteristics of translations produced by humans and machines, e.g. raw MT, post-edited MT and human translation.

Selected older work:

  • Ran a pilot study to assess the feasibility of using Machine Translation to assist with the professional translation of novels by means of post-editing. This study was funded by the EAMT and builds upon our evidence that literary-adapted MT results in promising results for closely-related languages (I, II)
  • Co-ordinated the EU-FP7 Abu-MaTran project, which deals with rapid development of Machine Translation systems for under-resourced languages. As part of the project I co-organised a National Linguistics Olympiad in Spain.
  • Adapted Active Learning to the task of Post-Editing of Machine Translation, which leads to more efficient and less tedious post-editing, as part of a Technology Innovation Development Award from Science Foundation Ireland (SFI-TIDA).
  • Devised a diagnostic evaluation metric for Machine Translation, as part of the CoSyne project.
  • Implemented a web services-based platform for Machine Translation tasks, as part of the PANACEA project.
  • In my PhD thesis I explored the automatic enrichment of linguistic resources (e.g. WordNet) with additional information from the Web 2.0 (e.g. Wikipedia).