Publication

Combining geometric, textual and visual features for predicting prepositions in image descriptions

Conference Article

Conference

Conference on Empirical Methods in Natural Language Processing (EMNLP)

Edition

2015

Pages

214-220

Doc link

http://www.emnlp2015.org/proceedings/EMNLP/pdf/EMNLP022.pdf

File

Download the digital copy of the doc pdf document

Abstract

We investigate the role that geometric, textual and visual features play in the task of predicting a preposition that links two visual entities depicted in an image. The task is an important part of the subsequent process of generating image descriptions. We explore the prediction of prepositions for a pair of entities, both in the case when the labels of such entities are known and unknown. In all situations we found clear evidence that all three features contribute to the prediction task.

Categories

computer vision.

Author keywords

computer vision, natural language processing

Scientific reference

A. Ramisa, J. Wang, Y. Lu, E. Dellandrea, F. Moreno-Noguer and R. Gaizauskas. Combining geometric, textual and visual features for predicting prepositions in image descriptions, 2015 Conference on Empirical Methods in Natural Language Processing, 2015, Lisbon, pp. 214-220.