Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Solids Characterization Using Modeling Wave Structures Read chapter Read first chapter

2003 | OriginalPaper | Chapter

Automatic Word Codification for the RECONTRA Connectionist Translator

Authors : Gustavo A. Casañ, M. Asunción Castaño

Published in: Pattern Recognition and Image Analysis

Publisher: Springer Berlin Heidelberg

Included in: Professional Book Archive

Get Access

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Previous work has shown that a simple recurrent neural model called RECONTRA is able to successfully approach simple text-to-text Machine Translation tasks in limited semantic domains. In order to deal with tasks of medium or large vocabularies, distributed representations of the lexicons are required in this translator. This paper shows a method for automatically extracting these distributed representations from perceptrons with output context.

previous chapter Determine the Composition of Honeybee Pollen by Texture Classification
next chapter The ENCARA System for Face Detection and Normalization
Metadata
Title
Automatic Word Codification for the RECONTRA Connectionist Translator
Authors
Gustavo A. Casañ
M. Asunción Castaño
Copyright Year
2003
Publisher
Springer Berlin Heidelberg
Book
Pattern Recognition and Image Analysis

Print ISBN: 978-3-540-40217-6

Electronic ISBN: 978-3-540-44871-6

Copyright Year: 2003

DOI
https://doi.org/10.1007/978-3-540-44871-6_20

Premium Partner

    Image Credits