Abstract:

Neural machine translation (NMT) has become the de facto automated translation technology for language pairs where enough data is available to build translation models. Despite its superior performance, NMT is still far from perfect. Two research areas that aim at making NMT more accurate or applicable in practical scenarios, such as human post-editing, are quality estimation and automatic post-editing. Quality estimation is the task of generating an estimate on the quality of a given machine translated text without access to a reference translation, while automatic post-editing is the task of automatically correcting the output of a machine translation system. NMT has brought new challenges to both areas, given its generally high translation quality as well as the fact that errors seem to be less predictable. In this presentation I will talk about current research in both quality estimation and automatic post-editing and the challenges faced when dealing with NMT output.

Bio:

Lucia Specia is Professor of Natural Language Processing at Imperial College London and University of Sheffield. Her research focuses on various aspects of data-driven approaches to language processing, with a particular interest in multimodal and multilingual context models and work at the intersection of language and vision. Her work can be applied to various tasks such as machine translation, image captioning, quality estimation and text adaptation. She is the recipient of the MultiMT ERC Starting Grant on Multimodal Machine Translation (2016-2021) and is currently involved in other funded research projects on machine translation, multilingual video captioning and text adaptation. In the past she worked as Senior Lecturer at the University of Wolverhampton (2010-2011), and research engineer at the Xerox Research Centre, France (2008-2009, now Naver Labs). She received a PhD in Computer Science from the University of São Paulo, Brazil, in 2008.