 |
|
|
|
|
|
|
|
Department of Information and Communication Technology
Language speech and Interfaces Group
|
Bios Alessandro Moschitti is an Assistant Professor at the Department of Communication and Information Technology of the University of Trento. He graduated in 1998 from the University of Rome "La Sapienza" with a Master Degree in Computer Science and obtained his PhD in Computer Science at the University of Rome "Tor Vergata" in 2003. He has worked for two years, between 2002 and 2004, as an associate researcher in the University of Texas at Dallas. His expertise concerns machine learning approaches to Natural Language Processing and Information Retrieval. In particular, he has designed applications of supervised and unsupervised learning for Text Categorization, Named Entity Recognition, Co-Reference Resolution, Text Summarization, Textual Entailment Recognition, Question Answering and Semantic Role Labeling. He has recently devised innovative kernels within Support Vector and other kernel-based machines for advanced syntactic/semantic processing. |
Research
Machine Learning for Natural Language Processing and Information Retrieval
-
Natural Language Processing Applications:
FrameNet and PropBank predicate argument extraction (Semantic Role Labeling),Relation Extraction, Co-reference resolution, Text Categorization, Textual Entailments, Question Answering, Word Sense Disambiguation, Named Entity Recognition, Named Entity Disambiguation, Spoken Dialog Systems and Text Summarization.
-
Kernel Methods, Support Vector Machines and on-line Learning:
Tree Kernel Engineering, Fast and Effective Tree Kernels, Kernels for Re-Ranking, Kernels for Bioinformatics, Fast Kernels over Tree Sets, Syntactic/Semantic Tree Kernels, Shallow Semantic Tree Kernels, Lexical Semantic Similarity Kernels.
Aims:
Studying and design of models combining innovative syntactic/semantic text representations and novel learning algorithms for the design of Information Retrieval systems. Such models may consider graph structures of events to compute both the answer to complex questions and its explanation in terms of graph dependency/implications.
Novel algorithms that both (a) easily learn Natural Language phenomena and other complex problems and (b) provide an explanation of the learnt model.
The Book
Automatic Text Categorization: from Information Retrieval to Support Vector Learning
A didactic book introducing Support Vector Machines and Text Categorization
Workshop on Learning Structured Information in Natural Language Applications
