Full Seminar Details
Semantic Analytics Group - University of Rome Tor Vergata
Structured Kernel-based Learning for Spatial Role Labeling
This event took place on Wednesday 03 July 2013 at 11:30
Referring to objects or entities in the space, as well as to relations holding among them, is one of the most important functionality in natural language understanding. As a result, the detection of spatial utterances finds many applications, such as in Spatal Relation Extraction, GPS navigation systems, or Human-Robot Interaction (HRI). In this presentation a system that participated to the Spatial Role Labeling SemEval task will be presented. The spatial roles classification is addressed as a sequence-based word classification problem: the SVM-hmm learning algorithm is applied, based on a simple feature modeling and a robust lexical generalization achieved through a Distributional Models of Lexical Semantics. In the identification of spatial relations, all roles found in a sentence are combined to generate candidate relations, later verified by a SVM classifier. The Smoothed Partial Tree Kernel is here applied, i.e. a convolution kernel that enhances both syntactic and lexical properties of the examples.
Watch the webcast replay >>
View all past events
We are also inviting top experts in AI and Knowledge Technologies to discuss major socio-technological topics with an audience that comprises both members of the Knowledge Media Institute, as well as the wider staff at The Open University. Differently from our seminar series, these events follow a Q&A format.