English
español
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10261/207493
Share/Impact:
Statistics |
![]() ![]() |
|
|
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |||
|
Title: | Semantic relatedness based re-ranker for text spotting |
Authors: | Sabir, Ahmed; Moreno-Noguer, Francesc ![]() |
Issue Date: | 3-Nov-2019 |
Publisher: | Association for Computational Linguistics |
Citation: | Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing: 3451–3457 (2019) |
Abstract: | Applications 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. |
Description: | Trabajo 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 |
URI: | http://hdl.handle.net/10261/207493 |
DOI: | http://dx.doi.org/10.18653/v1/D19-1346 |
Identifiers: | doi: 10.18653/v1/D19-1346 |
Appears in Collections: | (IRII) Libros y partes de libros |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
790025.pdf | 1,32 MB | Unknown | View/Open |
Show full item record
Review this work
Review this work
WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.