Please use this identifier to cite or link to this item:
Title: Predicting Visual Spatial Relations in the Maltese Language
Authors: Muscat, Adrian
Gatt, Albert
Keywords: Natural language processing (Computer science)
Human-computer interaction
Maltese language -- Prepositions
Issue Date: 2018
Publisher: University of Malta. Junior College
Citation: Muscat, A. & Gatt, A. (2018) Predicting Visual Spatial Relations in the Maltese Language. Junior College multi-disciplinary conference : research, practice and collaboration : Breaking Barriers : annual conference, Malta. 405-414.
Abstract: In this paper, the automatic detection of spatial prepositions between objects depicted in an image is studied. The ultimate aim is to incorporate the findings in a system that automatically describes images in a natural language. Whereas the explicit prediction of spatial relations in images has been previously studied in English and French, the work reported in this paper addresses relations in Maltese, an understudied language. A dataset consisting of images, spatial prepositions in Maltese, and a number of geometrical and language features is assembled from previous works. A number of predictive models are developed and the results are evaluated in terms of agreement with human-selected prepositions. The relative importance of the features in predicting the various relations is discussed and the paper concludes with a discussion on future work.
Description: Also published in Symposium Melitensia Vol. 15 (2019) p. 115-126
Appears in Collections:Breaking Barriers : Proceedings
Scholarly Works - FacICTCCE
SymMel, 2019, Volume 15
SymMel, 2019, Volume 15

Files in This Item:
File Description SizeFormat 
Adrian Muscat + 1.pdf1.62 MBAdobe PDFView/Open

Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.