K
Katerina Pastra
Researcher at Systems Research Institute
Publications - 35
Citations - 455
Katerina Pastra is an academic researcher from Systems Research Institute. The author has contributed to research in topics: Automatic summarization & Greek language. The author has an hindex of 11, co-authored 35 publications receiving 399 citations. Previous affiliations of Katerina Pastra include University of Sheffield.
Papers
More filters
Journal ArticleDOI
The minimalist grammar of action
TL;DR: This study presents a biologically inspired generative grammar of action, which employs the structure-building operations and principles of Chomsky's Minimalist Programme as a reference model and shows, how the tool role and the affected-object role of an entity within an action drives the derivation of the action syntax in this grammar.
Journal ArticleDOI
COGNIMUSE: a multimodal video database annotated with saliency, events, semantics and emotion with application to summarization
Athanasia Zlatintsi,Petros Koutras,Georgios Evangelopoulos,Nikolaos Malandrakis,Niki Efthymiou,Katerina Pastra,Alexandros Potamianos,Petros Maragos +7 more
TL;DR: In this paper, a multimodal video database, namely COGNIMUSE, annotated with sensory and semantic saliency, events, cross-media semantics, and emotion is presented.
Journal Article
COGNIMUSE: a multimodal video database annotated with saliency, events, semantics and emotion with application to summarization
Athanasia Zlatintsi,Petros Koutras,Nikolaos Malandrakis,Niki Efthymiou,Katerina Pastra,Alexandros Potamianos,Petros Maragos,Georgios Evangelopoulos +7 more
TL;DR: A multimodal video database, namely COGNIMUSE, annotated with sensory and semantic saliency, events, cross-media semantics, and emotion is presented and state-of-the-art algorithms are proposed for the detection of perceptually salient events from videos.
Proceedings ArticleDOI
Colouring summaries BLEU
Katerina Pastra,Horacio Saggion +1 more
TL;DR: The objective of this experiment is to explore whether a metric, originally developed for the evaluation of machine translation output, could be used for assessing another type of output reliably and put the feasibility of porting BLEU in different Natural Language Processing research areas under test.
Proceedings Article
How feasible is the reuse of grammars for Named Entity Recognition
TL;DR: Whether reusing existing Grammars for NE recognition instead of creating them from scratch is a viable solution to time constraints in developing grammars is investigated.