English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/207493
Share/Impact:
Statistics
logo share SHARE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:

Title

Semantic relatedness based re-ranker for text spotting

AuthorsSabir, Ahmed; Moreno-Noguer, Francesc ; Padró, Lluís
Issue Date3-Nov-2019
PublisherAssociation for Computational Linguistics
CitationProceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing: 3451–3457 (2019)
AbstractApplications such as textual entailment, plagiarism detection or document clustering rely on the notion of semantic similarity, and are usually approached with dimension reduction techniques like LDA or with embedding-based neural approaches. We present a scenario where semantic similarity is not enough, and we devise a neural approach to learn semantic relatedness. The scenario is text spotting in the wild, where a text in an image (e.g. street sign, advertisement or bus destination) must be identified and recognized. Our goal is to improve the performance of vision systems by leveraging semantic information. Our rationale is that the text to be spotted is often related to the image context in which it appears (word pairs such as Delta¿airplane, or quarters¿parking are not similar, but are clearly related). We show how learning a word-to-word or word-to-sentence relatedness score can improve the performance of text spotting systems up to 2.9 points, outperforming other measures in a benchmark dataset.
DescriptionTrabajo presentado en la Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, celebrada en Hong Kong ( China), del 3 al 7 de noviembre de 2019
Publisher version (URL)http://dx.doi.org/10.18653/v1/D19-1346
URIhttp://hdl.handle.net/10261/207493
Identifiersdoi: 10.18653/v1/D19-1346
Appears in Collections:(IRII) Libros y partes de libros
Files in This Item:
File Description SizeFormat 
790025.pdf1,32 MBUnknownView/Open
Show full item record
Review this work
 


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.