Alessandro Moschitti

Information Engineering and Computer Science Department

University of Trento

moschitti [at] disi.unitn.it

 



iKernels

My iKernels Group


 SVM-Light-TK

Corpora

Teaching Activities

Teaching    

Contacts


Main Links

 - iKernels
 - Research Program: Deep and
   Structured Machine Learning
 - DISI


Bios

Alessandro Moschitti is a professor of the CS Department of the University of Trento, Italy. He is currently a Principal Research Scientist of the Qatar Computing Research Institute (QCRI), within the Hamad Bin Khalifa University.
He obtained his PhD in NLP from the University of Rome in 2003. He has worked as a researcher associate at the University of Texas at Dallas and as a visiting professor of the Universities of Columbia, Colorado at Boulder, John Hopkins and of the Massachusetts Institute of Technology. Moreover, he has been a visiting research scientist of the IBM Watson Research center of NY, participating to the Jeopardy! Challenge.
His expertise concerns theoretical and applied Machine Learning in the areas of NLP, Information Retrieval and Data Mining. He has devised innovative kernels within support vector and other kernel-based machines for advanced syntactic/semantic processing, documented in about 250 scientific articles published in major venues. He has been the General Chair of EMNLP 2014 and the Program co-Chair of CoNLL 2015. He has been the PI for several European and USA projects. He is currently the PI (QCRI side) of a large collaboration project with MIT-CSAIL.
He has received four IBM Faculty awards, one Google Faculty award, five best paper awards and a researcher award from the University of Trento.

Research

Machine Learning for Natural Language Processing, Information Retrieval and Data Mining

The iKernels group led by Prof. Moschitti carries out advanced research on machine learning methods for syntactic and semantic processing of natural language. The group aims at improving the state of the art in Information Search and Retrieval by enriching language models (typically based on bag-of-words) with structural representations and semantics.

In the context of natural language, the group owns internationally recognized expertise in the following applications: Question Answering, FrameNet and PropBank Predicate Argument Extraction (Semantic Role Labeling), Relation Extraction, Syntactic and Semantic Parsing, Co-reference resolution, Text Categorization, Textual Entailment Recognition, Word Sense Disambiguation, Entity Recognition and Normalization, Opinion Mining, Speech and Noisy Text Processing, Text Similarity, Summarization and Link Open Data.

Regarding Machine Learning, the group has developed new theory and methods for Kernel Machines: Kernel Methods, Structural Kernels, Support Vector Machines, On-line Learning, Structured Output Spaces, Multi-label and Hierarchical Classification and Re-Ranking, and reverse kernel engineering for efficient processing and automatic feature engineering.
In the last two years, they have developed breakthrough models for Neural Networks in opinion mining, question answering and named entity recognition.

Theory and methods are also applied to broader ICT areas than natural language processing and Information Retrieval, such as Automatic Telecommunication Network Management, Electronic Failure detection, Anomaly Detection, Bioinformatics, Automatic Software Analysis (e.g., code classification).

Currently Funded Projects

Awards


Group Awards (selected)


Selected Past Funded Projects


Past Academic Support to the Research Community (selected)

PC committees: too many to be listed (see my Curriculum)


News/Current Activities

Organizer of SemEval-2017 Task 3: Community Question Answering



Editorial Boards

Journal of Natural Language Engineering (since 2013)

Journal of Artificial Intelligence Research  (since 2012)

Journal of Data Semantics
(since 2011)




  SIGIR 2013 
Kernel-based Learning to Rank with Syntactic and Semantic Structures

Slides

ACL 2012:
State-of-the-Art Kernels for Natural Language Processing
Slides

Coling 2010
Kernel Engineering for Fast and Easy Design of Natural Language Applications
Slides

Interspeech 2010
Kernel Engineering for Fast and Easy Design of Natural Language Applications
Slides


ACL Workshops

Co-Chair of TextGraphs-6: Graph-based Methods for NLP (ACL-NAACL 2011)

Co-Chair of Learning Structured Information in Natural Language Applications 
(EACL 2006)



workshops

  Web Question Answering, Beyond Factoids 2016

Semantic Matching in IR 2014


logo
EternalS Workshops

Co-Chair of 3rd International Workshop on Eternal Systems 2013 (EternalS'13)

Co-Chiar of 2nd International Workshop on Eternal Systems: JIMSE'12 (EternalS'12)

Co-Chair of 1st International Workshop on Eternal Systems (EternalS'11)

Chair of EternalS Track at ISoLA (International Symposium on Leveraging Applications of Formal Methods 2010)


John Hopkins Summer Workshop 
(JHU 2007)



Automatic Text Categorization: from Information Retrieval to Support Vector Learning

A didactic book introducing Support Vector Machines and Text Categorization