Are BLEU and Meaning Representation in Opposition?
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F18%3A10390141" target="_blank" >RIV/00216208:11320/18:10390141 - isvavai.cz</a>
Result on the web
<a href="http://aclweb.org/anthology/P18-1126" target="_blank" >http://aclweb.org/anthology/P18-1126</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Are BLEU and Meaning Representation in Opposition?
Original language description
One of possible ways of obtaining continuous-space sentence representations is by training neural machine translation (NMT) systems. The recent attention mechanism however removes the single point in the neural network from which the source sentence representation can be extracted. We propose several variations of the attentive NMT architecture bringing this meeting point back. Empirical evaluation suggests that the better the translation quality, the worse the learned sentence representations serve in a wide range of classification and similarity tasks.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
ISBN
978-1-948087-32-2
ISSN
—
e-ISSN
neuvedeno
Number of pages
10
Pages from-to
1362-1371
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Melbourne, Australia
Event date
Jul 15, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—