Dr. Giovanni Da San Martino

Scientist
Arabic Language Technologies

Connect with me

Looking around Doha, you get the feeling that the city is going to play a significant role in changing the composition of many fields in the near future. Having the chance to be a part of it is a great opportunity.”

Research Focus at QCRI

Dr. Da San Martino's main research interest is in the field of machine learning, applied to Natural Language Processing (NLP), including efficient and adaptive techniques for representing high dimensional data inside learning algorithms, such as kernel methods, with particular emphasis on designing fast learning algorithms for massive amounts of data and applications to NLP and biology domains.

The main focus of his research at QCRI is in designing and developing machine learning models of natural language for supporting advanced Arabic Language Technologies applications. A goal of his research includes devising techniques available through the Iyas framework, developed by the ALT group, in order to foster its use by researchers and industrial partners.

Previous Experience

Dr. Da San Martino received his PhD in Computer Science (CS) from the University of Bologna, Italy, and his MS and BS degrees in CS from the University of Pisa, Italy. From 2010 to 2014, he worked as a postdoctoral research fellow in the Department of Mathematics at the University of Padova, focusing on the design of efficient and adaptive representation for trees and graphs with kernel methods. In 2011, he was also a visiting researcher at the University of Wollongong, Australia.

He has published in top conferences and journals in the machine learning field. He is also a reviewer for the IEEE Transactions on Neural Networks journal and for several conferences.

Professional Experience


Professional Associations and Awards


Education

2006-2009   Doctor of Philosophy in Computer Science
                    University of Bologna

2003-2005   Master Degree in Computer Science
                    Mark 110/110
                    University of Pisa, Italy

1998-2003   Bachelor Degree in Computer Science
                    Mark 109/110
                    University of Pisa, Italy

Selected Research

Journal Papers
  • G. Da San Martino, A. Barrón-Cedeño, S. Filice, A. Moschitti  “On the Use of an Intermediate Class in Boolean Crowdsourced Relevance Annotations for Learning to Rank Comments”; Proceedings of SIGIR ’17. Shinjuku, Tokyo, Japan, 2017 
  • G. Da San Martino, S. Romeo, A. Barrón-Cedeño, S. Joty, L. Màrquez Villodre, A. Moschitti, P. Nakov; Cross-Language Question Re-ranking”; Proceedings of SIGIR ’17. Shinjuku, Tokyo, Japan, 2017
  • S. Romeo, G. Da San Martino, A. Barrón-Cedeño, A. Moschitti, Y. Belinkov, W. Hsu, Y. Zhang, M. Mohtarami, J. Glass; ”Neural Attention for Learning to Rank Questions in Community Question Answering”; Proceedings of the 26th International Conference on Computational Linguistics (COLING 2016), pages 1734–1745. Osaka, Japan, 2016
  • S.Filice, G. Da San Martino, A. Moschitti; ”Structural Representations for Learning Relations between Pairs of Texts”; Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, Beijing, China, 2015
  • F.Aiolli, G. Da San Martino, A. Sperduti;“An Efficient Topological Distance-based Tree Kernel”; Transactions on Neural Networks and Learning Systems journal, vol. 26, Issue 5, pages 1115-1120, 2009
  • F.Aiolli, G. Da San Martino, A. Sperduti; ”Route Kernels for Trees”, in Proceedings of the 26th International Conference on Machine Learning. Montreal, Canada, 2009
  • T. Sanavia, F. Aiolli, G. Da San Martino, A. Bisognin, B. Di Camillo, “Improving biomarker list stability by integration of biological knowledge in the learning process”, in Supplement of BMC Bioinformatics on BITS 2011, 2012

Book Chapters
  • F. Aiolli, G. Da San Martino, A. Sperduti, M. Hagenbuchner, ”Self-Organizing Maps for Structured Domains: Theory, Models and Learning of Kernels”, in Innovations in Neural Information Paradigms and Applications, Studies in Computational Intelligence Vol. 247/2009, pp. 9-42. BERLIN: Springer-Verlag Berlin Heidelberg (GERMANY), 2009.
Proceedings
  • F. Aiolli, G. Da San Martino, A. Sperduti, ”Route Kernels for Trees”, in Proceedings of the 26th International Conference on Machine Learning. June 14 - 18, 2009, Montreal, Canada.

  • G. Da San Martino, N. Navarin, A. Sperduti, “A Lossy Counting Based Approach for Learning on Streams of Graphs On a Budget”, Proceedings of the International Joint Conference on Artifical Intelligence (IJCAI), August 3 - 9, 2013, Beijing, China.
  • G. Da San Martino, N. Navarin, A. Sperduti, “A Tree-Based Kernel for Graphs”, in Proceedings of Siam International Conference on Data Mining, April 26 -28, 2012, Anaheim, California, USA.
  • G. Da San Martino, F. A. Cardillo, A. Starita, ”A new Swarm Intelligence Coordination Model Inspired by Collective Prey Retrieval and its Application to Image Alignment”, in Parallel Problem Solving from Nature (PPSN IX), Lecture notes in computer science. Springer-Verlag, Berlin. pp. 691-700.
  • F. Aiolli, G. Da San Martino, A. Sperduti, A. Moschitti, ”Fast On-Line Kernel Learning for Trees”, in Proceedings of the 2006 IEEE Conference on Data Mining. December 18 - 22, 2006, Hong Kong, China.
  • G. Da San Martino, N. Navarin, A. Sperduti, “A Memory Efficient Graph Kernel”, in Proceedings of the International Joint Conference on Neural Networks (IJCNN), June 10 - 15, 2012, Brisbane, Australia.
  • T. Sanavia, F. Aiolli, G. Da San Martino, A. Bisognin, B. Di Camillo, “Improving biomarker list stability by integration of biological knowledge in the learning process”, in Proceedings of ISMB/ECCB 2011 Conference.
  • F. Aiolli, G. Da San Martino, A. Sperduti, ”A Kernel Method for the Optimization of the Margin Distribution”, in Proceedings of the 18th International Conference on Artificial Neural Networks. September 3 - 6, 2008, Prague, Czech Republic.
  • M. Hagenbuchner, G. Da San Martino, A. C. Tsoi, A. Sperduti, ”Sparsity Issues in Self- Organizing-Maps for Structures”, in Proceedings of the 2011 ESANN Conference. April 27 - 29, 2011, Bruges, Belgium.
  • F. Aiolli, G. Da San Martino, A. Sperduti, ”A New Tree Kernel Based on SOM-SD”, Proceedings of the 20th International Conference on Artificial Neural Networks. September 15 - 18, 2010, Thessaloniki, Greece.
  • F. Aiolli, G. Da San Martino, A. Sperduti, ”Extending Tree Kernels with Topological Information”, in Proceedings of the 21th International Conference on Artificial Neural Networks. June, 14 - 17, Espoo, Finland.
  • F. Aiolli, G. Da San Martino, A. Sperduti, M. Hagenbuchner, ”Kernelized Self Organizing Maps for Structured Data”, in Proceedings of the 2007 ESANN Conference. April 24 - 27, 2007, Bruges, Belgium.
  • F. Aiolli, G. Da San Martino, A. Sperduti, A. Moschitti, ”Efficient Kernel-based Learning for Trees”, in Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Data Mining. April 1 - 5, 2007, Honolulu, Hawaii.
  • G. Da San Martino, F. A. Cardillo, A. Starita, ”A New Swarm Intelligence Algorithm for Image Alignment”, in Proceedings of the 3rd Institution of Engineering and Technology International Conference on Advances in Medical, Signal and Information Processing MEDSIP 2006, July 17 - 19, 2006, Glasgow, Scotland.
  • T. Sanavia, F. Aiolli, G. Da San Martino, A. Bisognin, B. Di Camillo, “Stable Feature Selection for Biomarker Discovery: Use of Biological Information”, in BITS Annual Meeting 2011, June 20 - 22, 2011, Pisa, Italy.
  • G. Da San Martino ”Kernel Methods for Tree Structured Data (Ph.D. Thesis)”, Technical Report, UBLCS-2009-04, Department of Computer Science, University of Bologna, 2009.

Connect with me

Follow Us

  • YouTube
  • Twitter
  • Facebook
  • RSS Feed
  • Linkedin
  • github-web.png
Back to Top

In the Media

Forbes fake news pic.jpg

Can AI Put An End To Fake News? Don't Be So Sure

07/10/2018

Fake news was the Collin’s word of the year for 2017 with good reason. In a year where politics-as-usual was torn apart at the seams, high-profile scandals rocked our faith in humanity and the ...

Read More

roadtracer.png

MIT/QCRI system uses machine learning to build road maps

22/04/2018

Map apps may have changed our world, but they still haven’t mapped all of it yet. Specifically, mapping roads can be difficult and tedious: even after taking aerial images, companies still have to ...

Read More

Economist story pic.JPG

Improving disaster response efforts through data

08/02/2018

Extreme weather events put the most vulnerable communities at high risk. How can data analytics strengthen early warning systems and and support relief efforts for communities in need? The size and ...

Read More

Upcoming Events

Past Events

2018

Eman interns pic 2017.jpg

QCRI Summer Internship Program

Download ICS File 06/05/2018  - 05/07/2018 , Hamad Bin Khalifa Research Complex

Each year, Qatar Computing Research Institute organizes a summer internship program for undergraduate students studying computer science, computer engineering and other disciplines. The internship is unpaid, and QCRI does not provide any visa support.

Read More

Regina

Public Talk by Prof. Regina Barzilay "Artificial Intelligence for Oncology: Learning to Cure Cancer from Images and Text"

Download ICS File 27/03/2018 ,

Artificial Intelligence for Oncology: Learning to Cure Cancer from Images and Text A talk by Professor Regina Barzilay, MIT CSAIL Winner of 2017 MacArthur ‘genius grant’ At Education City Student ...

Read More

Slide1.JPG

QCRI & MIT-CSAIL Annual Project Review 2018

Download ICS File 27/03/2018 ,

Executive Overview Sessions Open to public Date:    Tuesday, March 27, 2018 Time:    9:00AM – 3:00PM Venue:  HBKU Research Complex Multipurpose Room To view full agenda, please click here . To RSVP, ...

Read More

News Releases

Francisco Martin - Source_TelefonicaOpenFuture_.jpg

QCAI to Conduct Joint Machine Learning School with BigML

16/10/2018

Two-day crash course to provide hands-on introduction to machine learning for industry practitioners, developers, graduate students and undergraduates.

Read More

Ahmed at CSAIL.jpg

MIT-CSAIL hosts annual meeting highlighting collaboration with QCRI

14/10/2018

QCRI scientists travel to MIT-CSAIL campus in Boston to update research projects.

Read More

Ahmed Elmagarmid pic 1.jpg

The drivers behind our new Qatar Center for Artificial Intelligence (QCAI)

03/10/2018

QCRI's Executive Director Dr. Ahmed Elmagarmid explains why we have created a new AI hub in Qatar.

Read More