Loading...
Loading...

Go to the content (press return)

Multilingual, multi-scale and multi-layer visualization of sequence-based intermediate representations

Author
Escolano, C.; Ruiz, M.; Lacroux, E.; Vazquez, P.
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
2019-11-05
Book of congress proceedings
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations
First page
151
Last page
156
Publisher
Association for Computational Linguistics
Project funding
Deep learning technologies for speech and audio processing
Visualization, modeling, simulation and interaction with 3D models. Applications in life sciences and urban environments
Repository
http://hdl.handle.net/2117/184198 Open in new window
https://www.aclweb.org/anthology/D19-3000.pdf Open in new window
URL
https://www.aclweb.org/anthology/D19-3000/ Open in new window
Abstract
The main alternatives nowadays to dealwith sequences are Recurrent Neural Net-works (RNN), Convolutional Neural Networks(CNN) architectures and the Transformer. Inthis context, RNN’s, CNN’s and Transformerhave most commonly been used as an encoder-decoder architecture with multiple layers ineach module. Far beyond this, these architec-tures are the basis for the contextual word em-beddings which are revolutionizing most natural language downstream applications. However, intermediate layer re...
Citation
Escolano, C. [et al.]. Multilingual, multi-scale and multi-layer visualization of sequence-based intermediate representations. A: Conference on Empirical Methods in Natural Language Processing. "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations". Stroudsburg, PA: Association for Computational Linguistics, 2019, p. 151-156.
Keywords
Encoder-decoder architecture, Recurrent Neural Net-works, natural language processing.
Group of research
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
TALP - Centre for Language and Speech Technologies and Applications
VEU - Speech Processing Group
ViRVIG - Visualisation, Virtual Reality and Graphic Interaction Research Group

Participants