- -

Squeezing Bottlenecks: Exploring the Limits of Autoencoder Semantic Representation Capabilities

RiuNet: Institutional repository of the Polithecnic University of Valencia

Share/Send to

Cited by

Statistics

Squeezing Bottlenecks: Exploring the Limits of Autoencoder Semantic Representation Capabilities

Show full item record

Gupta, PA.; Banchs, R.; Rosso, P. (2016). Squeezing Bottlenecks: Exploring the Limits of Autoencoder Semantic Representation Capabilities. Neurocomputing. 175:1001-1008. doi:10.1016/j.neucom.2015.06.091

Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10251/82646

Files in this item

Item Metadata

Title: Squeezing Bottlenecks: Exploring the Limits of Autoencoder Semantic Representation Capabilities
Author:
UPV Unit: Universitat Politècnica de València. Escola Tècnica Superior d'Enginyeria Informàtica
Issued date:
Abstract:
[EN] We present a comprehensive study on the use of autoencoders for modelling text data, in which (differently from previous studies) we focus our attention on the various issues. We explore the suitability of two ...[+]
Subjects: Text representation , Deep autoencoder
Copyrigths: Reserva de todos los derechos
Source:
Neurocomputing. (issn: 0925-2312 )
DOI: 10.1016/j.neucom.2015.06.091
Publisher:
Elsevier
Publisher version: http://dx.doi.org/10.1016/j.neucom.2015.06.091
Project ID: info:eu-repo/grantAgreement/EC/FP7/269180/EU
Description: This is the author’s version of a work that was accepted for publication in Neurocomputing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neurocomputing 175 (2016) 1001–1008. DOI 10.1016/j.neucom.2015.06.091.
Thanks:
A significant part of this research work was conducted during the first author's attachment to the HLT department of I2R in Singapore. The work of the first and third authors was carried out in the framework of the WIQ-EI ...[+]
Type: Artículo

This item appears in the following Collection(s)

Show full item record