NMTVis - Trained Models for our Visual Analytics System

DOI

Trained models and vocabulary files for the use in our visual analytics system NMTVis. There are models for German to English and vice versa available for an LSTM-based and the Transformer architecture.

You may find the source code of our visual analytic system here or the most recent version of the system on GitHub: https://github.com/MunzT/NMTVis

There are also instructions available where to place the individual files to be used by the system.

Identifier
DOI https://doi.org/10.18419/DARUS-1850
Metadata Access https://darus.uni-stuttgart.de/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=doi:10.18419/DARUS-1850
Provenance
Creator Munz, Tanja ORCID logo; Väth, Dirk; Kuznecov, Paul; Vu, Ngoc Thang; Weiskopf, Daniel ORCID logo
Publisher DaRUS
Contributor Munz, Tanja
Publication Year 2021
Funding Reference Deutsche Forschungsgemeinschaft EXC-2075 - 390740016
Rights CC BY 4.0; info:eu-repo/semantics/openAccess; http://creativecommons.org/licenses/by/4.0
OpenAccess true
Contact Munz, Tanja (University of Stuttgart)
Representation
Resource Type Dataset
Format application/octet-stream
Size 758670845; 763380221; 1178915148; 1183624524; 2264943
Version 1.0
Discipline Other