End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F18%3A10390177" target="_blank" >RIV/00216208:11320/18:10390177 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification
Original language description
Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time. Non-autoregressive models enable the decoder to generate all output symbols independently in parallel. We present a novel non-autoregressive architecture based on connectionist temporal classification and evaluate it on the task of neural machine translation. Unlike other non-autoregressive methods which operate in several steps, our model can be trained end-to-end. We conduct experiments on the WMT English-Romanian and English-German datasets. Our models achieve a significant speedup over the autoregressive models, keeping the translation quality comparable to other non-autoregressive models.
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
<a href="/en/project/GBP103%2F12%2FG084" target="_blank" >GBP103/12/G084: Center for Large Scale Multi-modal Data Interpretation</a><br>
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 Conference on Empirical Methods in Natural Language Processing EMNLP 2018
ISBN
978-1-948087-84-1
ISSN
—
e-ISSN
neuvedeno
Number of pages
6
Pages from-to
3016-3021
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Bruxelles, Belgium
Event date
Oct 31, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—