Alessandro Moschitti

Assistant Professor

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
 - Language speech and Interaction
 - DISI

Bios

Alessandro Moschitti is a tenure professor of the Computer Science Department of the University of Trento. In 2003, he obtained his PhD in Computer Science at the University of Rome. He has worked as (i) an associate researcher for the University of Texas at Dallas, (ii) as a visiting professor for the Universities of Columbia (NY), Colorado and JHU and (iii) as visiting researcher for the IBM Watson, NY (since 2009 also participating at the Jeopardy! challenge). His expertise concerns theoretical and applied machine learning (ML) in the areas of NLP, IR and Data Mining. He has devised innovative kernels within support vector and other kernel-based machines for advanced syntactic/semantic processing. He is author or co-author of about 170 scientific articles published in major venues, e.g., ACL, SIGIR, ICDM, ICML, CIKM, ECML, EMNLP, IJCAI, etc., and journals, e.g., Computational Linguistics, IPM, DMKD, IS-IEEE, TASL-IEEE, etc.. He has been serving for important conferences, EMNLP, ACL, EACL, ECML PKDD, CoNLL, in several roles (General Chair, Sponsorship, Tutorial, Workshop co-chair and area co-chair for ACL (both semantics and ML tracks), IJCNLP (semantics), ECML PKDD (machine learning), IJCAI (NLP). Additionally, he is currently on the editorial board of JAIR, JNLE and JoDS. He has participated in seven EU and USA projects, e.g., LivingKnowledge, PrestoSpace, NAMIC, coordinated the entire consortium of the EU project, EternalS, and he currently is a partner coordinator of the LiMoSINe EU project. He has received three IBM Faculty Awards, one Google Faculty Award and several best paper awards (e.g., at ECML PKDD).


Research

Machine Learning for Natural Language Processing, Information Retrieval and data mining

The iKernels group led by Dr. Moschitti carries out advanced research on machine learning methods for syntactic and semantic processing of natural language. This aims at improving on 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 is developing 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.

Theory and methods are also applied to broader ICT areas than natural language processing and Information Retrieval, such as electronic feeder failure detection, bioinformatics, and automatic software processing (e.g., anomaly detection, code classification).

Currently Active Funded Projects

  • SenTube, Google EMEA, Switzerland, (PI for UNITN)
  • LiMoSINe, European Project, (Partner Coordinator)
  • Deep NLP for Italian, (Project Coordinator) together with FBK and IBM CAS Trento.


Awards


Group Awards



Selected Past Funded Projects


Past Academic Support to the Research Community (selected)

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

Tutorials


News/Current Activities


General Chair of EMNLP 2014

Sponsorship co-Chair for (E)ACL 2014 Conferences

My Tutorial at SIGIR 2013
  See link below
Kernel-based Learning to Rank with Syntactic and Semantic Structures

Area co-Chair (semantics) of
ACL 2013

Area Chair (Semantic Processing) of
 IJCNLP 2013


Senior PC member IJCAI 2013

JNLE Editorial Board (since 2013)

JAIR Editorial Board (since 2012)

JoDS Editorial Board (since 2011)



Past 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)


logo
Past 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