20 November 2018 - Lucia Specia: Seminar
Multimodal machine translation
Humans interact with the world through multiple modalities (hearing, vision, etc.). This is also true when understanding and generating language. Computational models for language processing, however, are traditionally limited to exploring language only (spoken or written). In this talk I will cover recent work in the area of multimodal machine learning for machine translation, where vision is used as additional modality, and where the goal is to achieve structured language grounding. I will also provide an overview on approaches that explore multimodality for language grounding in other sequence to sequence models: automatic speech recognition and spoken language translation.
Lucia Specia is Professor of Natural Language Processing at Imperial College London (since 2018) and at Sheffield University (since 2012). 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 has been 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 (H2020 Bergamot, APE-QUEST), multilingual video captioning (British Council MMVC) and text adaptation (H2020 SIMPATICO). In the past she worked as Senior Lecturer at the University of Wolverhampton, UK (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.