Assistant professor in Cognitive Science and Artificial Intelligence, Department of Cognitive Science and Artificial Intelligence, Tilburg University

Profile picutre

About

I am an assistant professor at the Department of Cognitive Science and Artificial Intelligence, Tilburg University (TiU). Between January and July 2020 I worked as an assistant professor in Computing the School of Computing, DCU. Prior to that (2017 - 2019) I worked as a post-doctoral researcher in the ADAPT centre, DCU. I hold a PhD in computer science engineering from KULeuven, Belgium. During my PhD studies I have worked on the design and development of artificial intelligence software for learning and reasoning with uncertain data. Before joining the ADAPT centre at DCU I was leading KantanLabs - a research and development group committed to advancing language technology within which I worked on introducing innovative technology such as efficient word reordering, improved alignment, neural MT and so on.

My academic interests are in the field of machine translation, cross-lingual information retrieval, natural language processing and subtopics related to optimisation, quality, performance, fairness, low-resources.

I have been involved in the teaching of courses on Linux, machine translation, machine learning and programming languages.

I have a strong industry experience having worked on projects with, among others, Microsoft, eBay and Huawei.

Starting from 1st of January 2021, I will be the scientific lead of the EU-funded project on translation of sign and oral languages: SignON

Teaching

Semester II, 2020/2021

  • 800883-B-6 Introduction to Deep Learning

Semester I, 2020/2021

Semester II, 2019/2020

Semester I, 2019/2020

Publications

2020

  • Xabier Soto, Dimitar Shterionov, Alberto Poncelas and Andy Way, Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translation, The 58th Annual Meeting of the Association for Computational Linguistics (ACL2020), Seattle, USA

  • Piyush Arora, Dimitar Shterionov, Yasufumi Moriya, Abhishek Kaushik, Daria Dzendzik and Gareth Jones An Investigative Study of Multi-Modal Cross-Lingual Retrieval, Workshop on Cross-Language Search and Summarization of Text and Speech (CLSSTS 2020), Marseilles, France

  • Dimitar Shterionov, Félix do Carmo, Joss Moorkens, Murhaf Hossari, Joachim Wagner, Eric Paquin, Dag Schmidtke, Declan Groves, and Andy Way, A Roadmap to Neural Automatic Post-Editing - an Empirical Approach, Machine Translation Journal (in press)

  • Félix do Carmo, Dimitar Shterionov, Joss Moorkens, Joachim Wagner, Murhaf Hossari, Eric Paquin, Dag Schmidtke, Declan Groves, and Andy Way, A Review of the State-of-the-art in Automatic Post-editing, Machine Translation Journal (in press)

2019

  • Alberto Poncelas, Maja Popovic, Dimitar Shterionov, Gideon Maillette de Buy Wenniger, Andy Way Combining SMT and NMT Back-Translated Data for Efficient NMT, Recent Advances in Natural Language Processing, Varna, Bulgaria, Sep. 2019

  • Eva Vanmassenhove, Dimitar Shterionov and Andy Way, Lost in translation: loss and decay of linguistic richness in Machine Translation, Machine Translation Summit XVII (MTSummit 2019), Dublin, Ireland, Aug. 2019.

  • Dimitar Shterionov, Félix do Carmo, Joss Moorkens, Murhaf Hossari, Eric Paquin, Dag Schmidtke, Declan Groves, and Andy Way, When less is more in neural quality estimation of machine translation. an industry case study.Machine Translation Summit XVII (MTSummit 2019), Dublin, Ireland, Aug. 2019.

  • Dimitar Shterionov, Joachim Wagner and Félix do Carmo, APE through neural and statistical MT with augmented data. ADAPT/DCU submission to the WMT 2019 APE Shared task, Jul. 2019, Fourth Conference on Machine Translation (WMT19), Florence, Italy, Aug. 1-2, 2019

  • Daniel Stein, Dimitar Shterionov, Andy Way, Towards language-agnostic alignment of product titles and descriptions: a neural approach Workshop on e-Commerce and NLP (ECNLP 2019), San Francisco, USA, May 2019

  • Dimitar Shterionov, Alberto Poncelas and Andy Way, Neural Machine Translation with and without parallel data - presentation, Computational Linguistics in the Netherlands (CLIN2019) conference, Groningen, the Netherlands, February 2019

  • Eva Vanmassenhove, Amit Moryossef, Alberto Poncelas, Andy Way and Dimitar Shterionov, ABI Neural Ensemble Model for Gender PredictionAdapt Bar-Ilan Submission for the CLIN29 Shared Task on Gender Prediction Computational Linguistics in the Netherlands (CLIN2019) conference, Groningen, the Netherlands, February 2019. Prepring available at: https://arxiv.org/abs/1902.08856

2018

  • Alberto Poncelas, Dimitar Shterionov, Andy Way, Gideon Maillette de Buy Wenniger and Peyman Passban Investigating Backtranslation in Neural Machine Translation, Proceedings of the EAMT2018 conference, Alicante, Spain, May 2018

2017

  • Dimitar Shterionov, Pat Nagle, Laura Casanellas, Riccardo Superbo, Tony O’Dowd, Andy Way, Human versus Automatic Quality Evaluation of NMT and PBSMT, DOI: https://doi.org/10.1007/s10590-018-9220-z, Machine Translation Journal, September 2017

  • Giulia Mattoni, Pat Nagle, Carlos Collantes, Dimitar Shterionov, Zero-Shot Translation for Indian Languages with Sparse Data User-track proceedings of MT Summit 2017, Nagoya, Japan, September 2017

  • Dimitar Shterionov, Pat Nagle, Laura Casanellas, Riccardo Superbo, Tony O’Dowd, Empirical evaluation of NMT and PBSMT quality for large-scale translation production, In electronic proceedings of EAMT2017, Prague, The Czech Republic, May 2017

  • Anita Ramm, Riccardo Superbo, Dimitar Shterionov, Tony O’Dowd, Alexander Fraser, Integration of a Multilingual Preordering Component into a Commercial SMT Platform, In The Prague Bulletin of Mathematical Linguistics, Number 108, June 2017, pp. 61–72

2016

  • Dimitar Shterionov, Marc Anthony Palminteri, Laura Casanellas, Jinhua Du, Tony O’Dowd, Andy Way, Improving KantanMT Training Efficiency with fast_align, In proceedings of Association for Machine Translation in the Americas 2016 Conference (AMTA2016), vol 2.

  • Dimitar Shterionov, Tony O’Dowd, Divide and Conquer Strategy for Large Data MT, In proceedings of Association for Machine Translation in the Americas 2016 Conference (AMTA2016), vol 2., Oct. 2016

  • Dimitar Shterionov, Machine Translation with Brains, In Multilingual Magazine, July/August 2016

2015

  • Theofrastos Mantadelis, Dimitar Shterionov, Gerda Janssens, Compacting Boolean Formulae for Inference in Probabilistic Logic Programming, In proceedings of International Conference on Logic Programming and Nonmonotonic Reasoning, (LPNMR) 2015, Sep. 2015

  • Daan Fierens, Guy Van den Broeck, Joris Renkens, Dimitar Shterionov, Bernd Gutmann, Ingo Thon, Gerda Janssens and Luc De Raedt, Inference and learning in probabilistic logic programs using weighted Boolean formulas, In Theory and Practice of Logic Programming, vol. 15, issue 03, May 2015

  • Dimitar Shterionov, Gerda JanssensCrucial Components in Probabilistic Inference Pipelines, In proceedings of Symposium of Applied Computing (SAC 2015), Salamanca, Spain, 13-17 April 2015

  • Dimitar Shterionov, Joris Renkens, Jonas Vlasselaer, Angelika Kimmig, Meert Wannes, Gerda Janssens, The Most Probable Explanation for Probabilistic Logic Programs with Annotated Disjunctions, In proceedings of the 24th International Conference on Inductive Logic Programming (ILP 2015), September 2015

2014

  • Dimitar Shterionov, Gerda Janssens, cProbLog: Restricting the Possible Worlds of Probabilistic Logic Programs, In First Workshop on Probabilistic Logic Programming (PLP 2014), Vienna, Austria, 17 July 2014

  • Shteliyan Shterionov, Dimitar Shterionov, Quantitative Methods for Investigating the Demographic Development of the Bulgarian Territories in 18th - 19th century, ( Демографската ситуация и развитието на България – форум / Demographic Situation and Development of Bulgaria – forum, Sofia, Bulgaria), 26-27 February 2014

2013

  • Dimitar Shterionov, Theofrastos Mantadelis, Gerda Janssens, Pattern-Based Compaction for ProbLog Inference, In proceedings of the 29th International Conference on Logic Programming (ICLP 2013), Aug. 2013

2012

  • Joris Renkens, Dimitar Shterionov, Guy Van den Broeck, Jonas Vlasselaer, Daan Fierens, Wannes Meert, Gerda Janssens, Luc De Raedt, ProbLog2: From probabilistic programming to statistical relational learning, In proceedings of the NIPS Probabilistic Programming Workshop (NIPS 2012), Dec. 2012

2011

  • Dimitar Shterionov, Gerda Janssens, Data acquisition and modeling for learning and reasoning in probabilistic logic environment, In proceedings of the 15th Portuguese Conference on Artificial Intelligence, Oct. 2011

2010

  • Dimitar Sht. Shterionov, Angelika Kimmig, Theofrastos Mantadelis, Gerda Janssens, DNF sampling for ProbLog inference, In proceedings of the 10th International Colloquium on Implementation of Constraint and LOgic Programming Systems (CICLOPS 2010), July 2010

Presentations

August2019_HAT2019_Workshop_MTSummit2019_dimitar_shterionov
ICT2018_networkingsession
ICT_Helsinki_2019_signon_presentation
January2019_CLIN2019_ZeroShot
July2019_WMT2019_APE_poster
March2019_WomensDay_dimitar_shterionov
November2019_ML_meetup

Projects

SignON

Access to information is a human right. In this modern, globalised world this implies access to multilingual content and cross-lingual communication with others. Crossing language barriers is essential for global information exchange and unobstructed, fair communication.

One in a thousand people in the EU (approximately half a million Deaf or hard-of-hearing people) communicates in one of 31 national or regional sign languages as their first language.

SignON - Sign Language Translation Mobile Application and Open Communications Framework - will cross the language barrier between Deaf sign language users, hard of hearing and hearing people. SignON will tear down this information barrier that currently exists.

Website:
www.signon-project.eu

GPU4EDU

As scientific fields such as Machine Learning, Deep Learning, Advanced Data Processing, Data Science and other AI subfields evolve at a fast pace, so should educational practices evolve too. The GPU4EDU project aims to provide new generations of students with access to modern facilities that allow them to gain up-to-date knowledge and progressive experience in the field of AI. That is, the aim of the GPU4EDU project is to bring the technical equipment at Tilburg University, Tilburg School of Humanities and Digital Sciences (TSHD) to a level that matches the requirements for current and future AI education. This project expands the hardware fleet of the School of Humanities and Digital Sciences for the educational needs of the Department of Cognitive Science and Artificial Intelligence with high-end, multi-GPU servers, accessible remotely and securely. Furthermore, these servers are dedicated to the educational needs of the students in courses taught within the CSAI department.

DL is a subfield of artificial intelligence that focuses on modeling non-linear problems using artificial neural networks. DL exploits complex neural network architectures which require substantial compute power. To deal with this complexity, a graphics processing unit (GPU) is more suitable than a central processing unit (CPU). This is largely because of the much higher number of cores in comparison to a CPU and substantial volume of dedicated memory that GPUs have. Currently, researchers that work on or with DL models rely heavily on GPU machines. Typically these are shared servers rather than personal workstations that are dedicated solely to working with DL models. Up till now, the available hardware dedicated to education did not include GPU servers. Students were required to resort to google cloud, other limited platforms or paid solutions. The GPU4EDU project has ensured a limited number of machines for student use and is a first step towards a larger educational infrastructure.

Website:
GPU4EDU