MT Summit XV | Keynote Speakers
AMTA and IAMT are proud to announce the following keynote speakers for MT Summit XV in Miami:
- KyungHyun Cho (NYU) — Neural Machine Translation: Introduction and Progress Report
Neural machine translation is a recently proposed framework for machine translation, which is purely based on neural networks. Neural machine translation radically departs from the existing, widely-used, often phrase-based statistical machine translation by viewing the task of machine translation as a supervised, structured output prediction problem and solving it with recurrent neural networks. In this talk, I will describe in detail what neural machine translation is and discuss recent advances which have made it possible for neural machine translation system to be competitive with the conventional statistical approach.
Kyunghyun Cho is an assistant professor in the Department of Computer Science, Courant Institute of Mathematical Sciences and the Center for Data Science at New York University (NYU) (starting September, 2015). Previously, he was a postdoctoral researcher at the University of Montreal under the supervision of Prof. Yoshua Bengio after obtaining a doctorate degree at Aalto University (Finland) in early 2014. Kyunghyun’s main research interests include neural networks, generative models and their applications, especially, to language understanding.
- Macduff Hughes (Google) — Machine Translation: The Next Decade
The past decade has seen machine translation move out of the lab and into widespread practical use on computers and smart phones. The widespread use of MT in practice has shown the enormous demand for automated translation, and yielded insights into both the power and the limitations of current technology. New developments show promise for expanding the usefulness of MT, and we look at some of the trends that might shape the next decade of machine translation. Deep neural networks are proving to have power in many aspects of translation. Advances in natural language understanding make it possible to train systems to preserve meaning. The power of crowds can deliver quick corrections to errors and translations of newly emerging colloquialisms and slang. Finally, advances in voice recognition and machine vision are creating new applications and user experiences.
Macduff Hughes has led the Google Translate team as Engineering Director since 2012. He has worked at Google since 2007, having previously led the Google Voice and Google Accounts teams. He has a bachelor’s degree from Stanford University and did graduate studies at the University of Trier and Columbia University.
- Kevin Duh (NAIST/JHU) — Continuous Wide-Band Machine Translation – Report from the 2015 Jelinek Summer Workshop
Continuous space models of language (CSMs) are compelling for machine translation since they permit a diverse variety of contextual information to be considered when making decisions about local (e.g., lexical and morphological) and global (e.g., sentence structure and discourse) translation decisions. They thus promise to make machine translation more practical with fewer examples of parallel sentences by leveraging limited parallel data more effectively. I will present our workshop experiences and efforts in: (i) developing tools to make experimentation with continuous space translation models practical; (ii) demonstrating their effectiveness in low-resource translation scenarios; and (iii) developing models that condition on non-local context, in particular discourse structure, to improve the state of the art in high-resource scenarios.
Kevin Duh is an assistant professor at the Nara Institute of Science and Technology (NAIST), Graduate School of Information Science. He received his B.S. in 2003 from Rice University, and PhD in 2009 from the University of Washington, both in Electrical Engineering. Prior to joining NAIST, he worked at the NTT Communication Science Laboratories (2009-2012). His research interests lie at the intersection of Natural Language Processing and Machine Learning, in particular on areas relating to machine translation, semi-supervised learning, and deep learning.
- Spyridon Pilos (European Commission MT Program) — Automated Translation Connecting Europe
The European Commission is currently creating an ecosystem of pan-European online public services funded through the Connecting Europe Facility (CEF). A core building block of this ecosystem is a platform to support and facilitate translation automation for the CEF digital services and for public administrations in the European Union and its Member States. The starting point is its existing machine translation service, MT@EC, and the objective is to bring together the language resources and the best tools from market and research to support all EU languages and serve the multilingual needs of the citizens. With the CEF program, new emphasis is given to deployment of mature language technologies, many of which result from earlier research and innovation projects supported by the EU since many years.
Spyridon Pilos studied mathematics at the University of Athens and joined the European Commission as a translator in 1992. He then worked as administrator in the areas of statistics and digital content. In 2009 he returned to Directorate-General for Translation as head of the language applications sector of the IT unit, where he led the development of the machine translation system MT@EC, operational since June 2013 and used by all EU institutions, public administrations and online services. He is currently also working for the implementation of CEF.AT, the Automated Translation platform serving the CEF digital service infrastructures.
- Matt Post (Johns Hopkins University) — Speech-to-text translation of conversational Pashto
Matt Post is a Senior Research Scientist at the Human Language Technology Center of Excellence (HLTCOE) at Johns Hopkins University, where he works on machine translation. His interests are in statistical machine translation and other text-to-text rewriting tasks, with a focus on syntactic methods. He has co-organized the Workshop on Statistical Machine Translation for the past four years, is currently serving a two-year term on the NAACL executive committee, and maintains the open-source Joshua machine translation toolkit. He received his Ph.D. in computer science from the University of Rochester.