Research Interests :: Current Work :: Contacts

Since January 2010, I hold a post-doc position at FBK and I'm involved in the PESCaDO (Personalized Environmental Service Configuration and Delivery Orchestration) and in the TERENCE (Adaptive Learning System for Reasoning about Stories with Poor Comprehenders and their Educators) European projects.

Research Interests

I have been working on annotation projection using parallel corpora and on the analysis of predicate-argument structure following the frame semantics paradigm. In March 2010 I defended my PhD thesis "Semi-automatic techniques for extending the FrameNet lexical database to new languages" at University of Venice, Dept. of Language Sciences.

I am interested in investigating different approaches to extend and enrich FrameNet-like resources. In particular, I contributed to the development and evaluation of an automatic mapping between FrameNet and WordNet and to the extraction of Wikipedia sentences with frame information. Besides, I have automatically enriched frame elements with synset information. In general, I am interested in analyzing the connections between linguistic resources and information from the Semantic Web, with the goal of performing Deep Semantic Understanding.

I have also worked on discourse analysis, in particular on the adaptation of the Penn Discourse framework to spontaneous dialogs of spoken Italian. Besides, I have contributed to the development of a discourse parser in collaboration with the Signals and Interactive Systems Lab at University of Trento.

For more recent information on what I am currently doing, give a look at my tweets on the right.

Current Work

Ongoing research projects involve:

• PESCaDO European Project: I am in charge of distilling content from multilingual web-sites in the environmental domain and to perform key-concept extraction from English, Finnish and Swedish documents. My activities in the project support on the one hand the discovery of environmental nodes on the web and on the other hand the development, extension and evaluation of domain-specific ontologies. I contributed to the development and integration of the terminological module in the Moki platform for knowledge modeling (try it out!)
• TERENCE European Project: I am in charge of developing a system for temporal processing of Italian stories. I have also contributed to the development of a system for measuring text readability and classifying documents into language proficiency levels.

Contacts

My email at FBK is satonelli [at] fbk.eu