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

Giovanni’s main research interest is in the field of machine learning, applied to Natural Language Processing (NLP), and it includes efficient and adaptive techniques for representing high dimensional data inside learning algorithms, such as kernel methods, and 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 will be to design and develop machine learning models of natural language for supporting advanced ALT applications. A goal of his research will be to make the developed techniques available through the Iyas framework, developed by the ALT group, in order to foster its use by researchers and industrial partners.

Previous Experience

Giovanni 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.

Giovanni 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
  • 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.

  • G. Da San Martino, A. Sperduti, ”Mining Structured Data”, in IEEE Computational Intelligence Magazine. Vol. 5, Issue 1, Feb. 2010 Pages:42 - 49 .
  • F. Aiolli, G. Da San Martino, A. Sperduti, M. Hagenbuchner, ”Learning Non-sparse Kernels by Self-Organizing Maps for Structured Data”, in IEEE Transactions on Neural Networks. Vol. 20, Issue 12, Dec. 2009 Pages:1938 - 1949
  • F. Aiolli, G. Da San Martino, A. Sperduti, “An Efficient Topological Distance-based Tree Kernel”, to appear in the Transactions on Neural Networks and Learning Systems journal.

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

Luis Luque El Correo.jpg

Entrevista con Luis Fernández Luque, cofundador de Salumedia e investigador del Qatar Computing Research Institute

08/01/2018

Si quiere buscar un ejemplo de ciudadano del mundo, de los que al cabo del año vive y trabaja desde numerosos países, y a través de internet, esté donde esté, desarrolla en remoto actividades para ...

Read More

Raghvendra science pic.jpg

Gene fusion shifts cell activity into high gear, causing some cancer

04/01/2018

The fusion of two adjacent genes can cause cancer by kicking mitochondria into overdrive and increasing the amount of fuel available for rampant cell growth, researchers at Columbia University ...

Read More

BBC newshack pic.jpg

QCRI team wins SUMMA BBC #NewsHack 'Best Audience Experience' prize

13/12/2017

Congratulations to Ahmed Ali, Yifan Zhang and Fahim Dalvi for winning the prize of the “Best Audience Experience” category at the news hack hosted by SUMMA and BBC in London on 21-22 November with ...

Read More

Upcoming Events

2017

after school pic.JPG

QCRI's Creative Space launches free after-school computing courses for teenagers

Download ICS File 01/11/2017  - 20/12/2018 ,

We offer an App Inventor Course in Arabic for students aged 13-15 and an Arduino Programming Course in English for students aged 14-18. Courses are free. Please register quickly as places are limited.

Read More

Past Events

Summer Camp 2.jpg

QCRI conducts first summer computing camps for kids

Download ICS File 16/07/2017  - 27/07/2017 ,

Children and teenagers have been given a rare chance to develop their computing skills with world-class computing scientists at the first summer computing camp conducted by the Qatar Computing ...

Read More

CS 1.jpg

QCRI’s Creative Space holds Open House event for kids

Download ICS File 20/05/2017 ,

The Qatar Computing Research Institute’s new Creative Space, which conducts fun activities to teach children computing skills, has successfully held its first Open House event. About 100 children ...

Read More

News Releases

Jim Jansen pic preferred.jpg

Research by QCRI's Jim Jansen among most influential of decade: top journals

13/12/2017

QCRI Social Computing group's principal scientist achieves rare honor.

Read More

yelena pic.JPG

#Halal now a lifestyle definition on Instagram

29/11/2017

The word “halal” is no longer being defined only in a religious context but is becoming a lifestyle term associated with health and fashion around the globe, a new study of Instagram posts led by ...

Read More

Dr. Mokbel.jpg

QCRI’s Mohamed Mokbel named Distinguished Scientist by world’s largest computing society ACM

21/11/2017

Chief scientist among only 43 scientists globally - and the only one from the Middle East - to be selected for the honor in 2017.

Read More