Full Seminar Details

Emanuele Bastianelli

Semantic Analytics Group - University of Rome Tor Vergata

 Emanuele Bastianelli
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 >>


Senior Research Fellow

Knowledge Media Institute (KMi)
50,618 - 56,950 (Grade AC4)
Based in Milton Keynes
Permanent position

WE ACCEPT APPLICATIONS FROM CITIZENS GLOBALLY The Knowledge Media Institute (KMi) is one of the top research centres in the world in the area of knowledge and media technologies, and we offer a creative and flexible working environment. KMi is a...


Knowledge Media Institute
The Open University
Walton Hall
Milton Keynes
United Kingdom

Tel: +44 (0)1908 653800

Fax: +44 (0)1908 653169

Email: KMi Support


If you have any comments, suggestions or general feedback regarding our website, please email us at the address below.

Email: KMi Development Team