Loading...
Loading...

Go to the content (press return)

Semantic relatedness based re-ranker for text spotting

Author
Sabir, A.; Moreno-Noguer, F.; Padro, L.
Type of activity
Presentation of work at congresses
Name of edition
2019 Conference on Empirical Methods in Natural Language Processing
Date of publication
2019
Presentation's date
2019-11
Book of congress proceedings
Proceedings of EMNLP 2019
First page
3451
Last page
3457
Project funding
HuMoUR: Markerless 3D human motion understanding for adaptive robot behavior - TIN2017-90086-R
Repository
http://hdl.handle.net/2117/181252 Open in new window
URL
https://www.aclweb.org/anthology/D19-1346.pdf Open in new window
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 id...
Citation
Sabir, A.; Moreno-Noguer, F.; Padro, L. Semantic relatedness based re-ranker for text spotting. A: Conference on Empirical Methods in Natural Language Processing. "Proceedings of EMNLP 2019". 2019, p. 3451-3457.
Keywords
Deep learning, Text spotting
Group of research
GPLN - Natural Language Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
ROBiri - IRI Robotics Group
TALP - Centre for Language and Speech Technologies and Applications

Participants