*KEYNOTE SPEAKERS

For the upcoming TSD2017, the following outstanding and eminent keynote speakers with respectable expertise in the conference interest fields agreed to give their respective pieces of speech:

See the next section below for details about the speeches (topics, abstracts). By clicking onto the title of the speech (in italics) or the PDF icon behind it, you can see the PDF with the presentation (if available).

SPEAKERS' & SPEECHES' DETAILS

Eva Hajicova

Eva Hajičová

Professor of Linguistics – Institute of Formal and Applied Linguistics, Charles University, Czechia

A glimpse under the surface: language understanding may need deep syntactic structures 

Abstract:  Extended abstract in PDF PDF (77 KB)

Biography:  Eva Hajičová, born August 23, 1935, is a professor of linguistics at the Faculty of Mathematics and Physics, Charles University, Prague. She graduated in English and Czech at the Faculty of Philosophy of Charles University and got her Ph.D. degree as well as the highest academic degree of DrSc in general and computational linguistics at the same university. Her interests cover theoretical linguistics as well as computational applications; she has concentrated on the semantic structure of the sentences, on the discourse phenomena and on different topics in computational linguistics.

She is a member of a number of editorial boards of international journals (Journal of Pragmatics, Computers and Artificial Intelligence, Linguistica Pragensia, Kybernetika) and was the editor-in-chief of Prague Bulletin of Mathematical Linguistics. She was the first president of the European Chapter of the Association of Computational Linguistics (1982-1987) and the president of the international Association for Computational Linguistics in 1998; she also was the President of the Societas Linguistica Europaea, 2006-2007, and is a member of the International Committee of Computational Linguistics.

She was the chairperson of the Prague Linguistic Circle and is a honorary member of Societas Linguistica Europaea, a member of Academia Europaea and of several Czech scientific societies. She was awarded the Alexander von Humboldt Research Prize in 1995, the Medal of the minister of Education of Czech Republic in recognition of the pedagogical and scientific work in computational linguistics, 2003 and the ACL Life Achievement Award 2006. She is an elected member of the Learned Society of Czech Republic (since 2004).
Tomas Mikolov

Tomáš Mikolov

Research Scientist – Facebook AI Research Group, USA

Towards building intelligent machines that we can communicate with 

Abstract:  In the recent years, there has been growing interest in development of general artificial intelligence systems. I will describe some of our recent attempts to build such intelligent system, starting by specifying the end goal: A machine that accomplishes tasks via natural language. Further, I will discuss several simplifications we are considering to make this research project more manageable: Teaching the AI to communicate at first in simulated environments, and early focus on incremental learning to efficiently use small number of training examples. I will present a dataset that we recently published to help the research community in achieving these goals.

Biography:  Tomáš Mikolov is a research scientist at Facebook AI Research group since May 2014. Previously he has been member of the Google Brain team, where he developed and implemented efficient algorithms for computing distributed representations of words (the word2vec project). He obtained his PhD from the Brno University of Technology (Czech Republic) in 2012 for his work on recurrent neural network-based language models (RNNLM). His long term research goal is to develop intelligent machines that people can communicate with and use to accomplish complex tasks.
Michael Picheny

Michael Picheny

Senior Manager of Watson Multimodal – Thomas J. Watson Research Center, Yorktown Heights, NY, USA

Future challenges for speech recognition: fast adaptation and building low resource language systems 

Abstract: Not yet available.

Biography:  Michael Picheny is the Senior Manager of Watson Multimodal in the Watson Group at the IBM T. J. Watson Research Center. Michael has worked in the Speech Recognition area since 1981, joining IBM after finishing his doctorate at MIT. He has been heavily involved in the development of almost all of IBM's recognition systems, ranging from the world's first real-time large vocabulary discrete system through IBM's product lines for telephony and embedded systems. He has published numerous papers in both journals and conferences on almost all aspects of speech recognition. He has received several awards from IBM for his work, including a corporate award, three outstanding Technical Achievement Awards and two Research Division Awards. He is the co-holder of over 30 patents and was named a Master Inventor by IBM in 1995 and again in 2000. Michael served as an Associate Editor of the IEEE Transactions on Acoustics, Speech, and Signal Processing from 1986-1989, was the chairman of the Speech Technical Committee of the IEEE Signal Processing Society from 2002-2004, and is a Fellow of the IEEE. He served as an Adjunct Professor in the Electrical Engineering Department of Columbia University in 2009 and 2012 and co-taught a course in speech recognition. He was a member of the board of ISCA (International Speech Communication Association) from 2005-2013 and named an ISCA Fellow in 2014. He was the co-general chair of the IEEE ASRU 2011 Workshop in Hawaii.
Rico Sennrich

Rico Sennrich

Research Associate – Institute for Language, Cognition and Computation, The University of Edinburgh, UK

Neural machine translation – what's linguistics got to do with it? 

Abstract:  Neural machine translation has obtained impressive results in the last few years, establishing itself as the new state of the art. This has been achieved by learning from raw text, without explicit linguistic knowledge. In this talk, I will discuss the capability of sequence-to-sequence models to learn linguistic phenomena from text, and will present recent research on incorporating explicit linguistic structure into the models.

Biography:  Rico Sennrich is a research associate at the Institute for Language, Cognition and Computation, University of Edinburgh. He received his PhD in Computational Linguistics from the University of Zurich in 2013, and has since worked at the University of Edinburgh, first funded by a SNSF post-doctoral fellowship, and now participating in EU-funded projects on machine translation (TraMOOC, QT21, SUMMA). His recent research has focused on modelling linguistically challenging phenomena in machine translation, including grammaticality, productive morphology, domain effects, and pragmatic aspects. His work on syntax-based and neural machine translation has resulted in top-ranked submissions to the annual WMT shared translation task in three consecutive years.
Lucia Specia

Lucia Specia

Professor of Language Engineering – NLP Group, Dept. of Computer Science, The University of Sheffield, UK

A picture is worth a thousand words: towards multimodal, multilingual context models 

Abstract:  In Computational Linguistics, work towards understanding or generating language has been primarily based solely on textual information. However, when we humans process a text, be it written or spoken, we also take into account cues from the context in which such a text appears, in addition to our background and common sense knowledge. This is also the case when we translate text. For example, a news article will often contain images and may also contain a short video and/or audio clip. Users of social media often post photos and videos accompanied by short textual descriptions. The additional information can help minimise ambiguities and elicit unknown words. In this talk I will introduce a recent area of research that addresses the automatic translation of texts from rich context models that incorporate multimodal information, focusing on visual cues from images. I will cover some of our recent work analysing how humans perform translation in the presence/absence of visual cues and then move on to datasets and computational models proposed for this problem.

Biography:  Lucia Specia is a professor of language engineering at the Department of Computer Science of the University of Sheffield. Her research focuses on various aspects of data-driven approaches to multilingual language processing. She is the recipient of an ERC Starting Grant on Multimodal Machine Translation (2016-2021) and is involved in other funded research projects on Machine Translation (QT21 21 and CRACKER) and Text Adaptation (SIMPATICO). Before joining the University of Sheffield in 2012, she was Senior Lecturer at the University of Wolverhampton, UK (2010-2011), and research engineer at the Xerox Research Centre, France (2008-2009). She received a PhD in Computer Science from the University of São Paulo, Brazil, in 2008. She has published over 100 research papers in peer-reviewed journals and conference proceedings. She has served as area and programme chair, and on programme committees of numerous leading international conferences and journals, and organised a number of workshops and shared tasks in the area of NLP.
Back to top...