NMTVis - Extended Neural Machine Translation Visualization System
T. Munz, D. Väth, P. Kuznecov, N. Vu, and D. Weiskopf. Software, (2022)Related to: T. Munz, D. Väth, P. Kuznecov, N. T. Vu, and D. Weiskopf. "Visualization-based improvement of neural machine translation", Computers & Graphics, 2021. doi: 10.1016/j.cag.2021.12.003.
DOI: 10.18419/darus-2124
Abstract
NMTVis is a web-based visual analytics system to analyze, understand, and correct translations generated with neural machine translation. First, a document can be translated using a neural machine translation model (we support an LSTM-based and the Transformer architecture). Afterward, users can find mistranslated sentences, explore and correct these sentences and retrain the model to generate a better translation for the whole document. Our approach targets the correction of domain-specific documents. This extended version of our visual analytics system provides additional visualization and interaction techniques as well as scripts for computer-based evaluation of our approach. You can find important information about our system here and an introduction to our system here.
Munz, Tanja/University of Stuttgart, Väth, Dirk/University of Stuttgart, Kuznecov, Paul/University of Stuttgart, Vu, Ngoc Thang/University of Stuttgart, Weiskopf, Daniel/University of Stuttgart
Related to: T. Munz, D. Väth, P. Kuznecov, N. T. Vu, and D. Weiskopf. "Visualization-based improvement of neural machine translation", Computers & Graphics, 2021. doi: 10.1016/j.cag.2021.12.003
%0 Generic
%1 munz2022nmtvis
%A Munz, Tanja
%A Väth, Dirk
%A Kuznecov, Paul
%A Vu, Ngoc Thang
%A Weiskopf, Daniel
%D 2022
%K EXC2075 PN6 PN6-4
%R 10.18419/darus-2124
%T NMTVis - Extended Neural Machine Translation Visualization System
%X NMTVis is a web-based visual analytics system to analyze, understand, and correct translations generated with neural machine translation. First, a document can be translated using a neural machine translation model (we support an LSTM-based and the Transformer architecture). Afterward, users can find mistranslated sentences, explore and correct these sentences and retrain the model to generate a better translation for the whole document. Our approach targets the correction of domain-specific documents. This extended version of our visual analytics system provides additional visualization and interaction techniques as well as scripts for computer-based evaluation of our approach. You can find important information about our system here and an introduction to our system here.
@misc{munz2022nmtvis,
abstract = {NMTVis is a web-based visual analytics system to analyze, understand, and correct translations generated with neural machine translation. First, a document can be translated using a neural machine translation model (we support an LSTM-based and the Transformer architecture). Afterward, users can find mistranslated sentences, explore and correct these sentences and retrain the model to generate a better translation for the whole document. Our approach targets the correction of domain-specific documents. This extended version of our visual analytics system provides additional visualization and interaction techniques as well as scripts for computer-based evaluation of our approach. You can find important information about our system here and an introduction to our system here.},
added-at = {2024-03-26T11:56:13.000+0100},
affiliation = {Munz, Tanja/University of Stuttgart, Väth, Dirk/University of Stuttgart, Kuznecov, Paul/University of Stuttgart, Vu, Ngoc Thang/University of Stuttgart, Weiskopf, Daniel/University of Stuttgart},
author = {Munz, Tanja and Väth, Dirk and Kuznecov, Paul and Vu, Ngoc Thang and Weiskopf, Daniel},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/297c16a709b140b9f490d8a254107e02f/exc2075},
doi = {10.18419/darus-2124},
howpublished = {Software},
interhash = {2ca9d88c72f0d61dcd18e560d7385e62},
intrahash = {97c16a709b140b9f490d8a254107e02f},
keywords = {EXC2075 PN6 PN6-4},
note = {Related to: T. Munz, D. Väth, P. Kuznecov, N. T. Vu, and D. Weiskopf. "Visualization-based improvement of neural machine translation", Computers & Graphics, 2021. doi: 10.1016/j.cag.2021.12.003},
orcid-numbers = {Munz, Tanja/0000-0003-3960-3290, Weiskopf, Daniel/0000-0003-1174-1026},
timestamp = {2024-03-26T18:13:44.000+0100},
title = {NMTVis - Extended Neural Machine Translation Visualization System},
year = 2022
}