Visualizing Neural Machine Translation Attention and Confidence
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F17%3A10372033" target="_blank" >RIV/00216208:11320/17:10372033 - isvavai.cz</a>
Result on the web
<a href="https://ufal.mff.cuni.cz/pbml/109/art-rikters-fishel-bojar.pdf" target="_blank" >https://ufal.mff.cuni.cz/pbml/109/art-rikters-fishel-bojar.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1515/pralin-2017-0037" target="_blank" >10.1515/pralin-2017-0037</a>
Alternative languages
Result language
angličtina
Original language name
Visualizing Neural Machine Translation Attention and Confidence
Original language description
In this article, we describe a tool for visualizing the output and attention weights of neural machine translation systems and for estimating confidence about the output based on the attention. Our aim is to help researchers and developers better understand the behaviour of their NMT systems without the need for any reference translations. Our tool includes command line and web-based interfaces that allow to systematically evaluate translation outputs from various engines and experiments. We also present a web demo of our tool with examples of good and bad translations: http://ej.uz/nmt-attention
Czech name
—
Czech description
—
Classification
Type
J<sub>ost</sub> - Miscellaneous article in a specialist periodical
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
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
The Prague Bulletin of Mathematical Linguistics
ISSN
0032-6585
e-ISSN
—
Volume of the periodical
109
Issue of the periodical within the volume
1
Country of publishing house
CZ - CZECH REPUBLIC
Number of pages
12
Pages from-to
39-50
UT code for WoS article
—
EID of the result in the Scopus database
—