Even if not perfect, machine translation (MT) is now becoming reliable enough to support the translation industry. As a result, more and more professional translators post-edit the output of an MT system. This leads to large quantities of MT translated data that are transformed into perfect translations by fixing MT errors. Within this process, translators have to deal with repetitive and annoying MT errors as well as with the inability of the MT systems to adapt to new domains and styles. Both aspects have an enormous impact on translators' work.
This webinar introduces automatic post-editing (APE), a research strand in MT aiming at fixing MT errors by looking at the corrections made by professional translators. The presentation also discusses the use of an APE system in the CAT scenario, where a stream of sentences need to be processed in real-time.
This webinar is part of the Research and Innovation Action "Quality Translation 21 (QT21)." This project has received funding from the European Union's Horizon 2020 program for ICT under grant agreement no. 645452.
Marco is a researcher in the Human Language Technology Machine Translation (HLT-MT) group at Fondazione Bruno Kessler (FBK) in Trento, Italy. Before joining FBK, he worked as research engineer at the European Commission Joint Research Centre in Italy, at the University of Bristol and at the Xerox Research Centre Europe. He received his Ph.D. degree in Computer Science from the University of Siena, Italy in 2006. His current research is centered around applying machine learning techniques to MT, with particular emphasis on exploiting post-edited data to improve MT quality. He is involved in various funded research projects, including the European initiatives QT21 (Quality Translation 21) and MMT (Modern Machine Translation). He has co-authored more than 80 peer-reviewed scientific publications.