Repository logo
 

Research Data Supporting "Syntactically Guided Neural Machine Translation"

Repository URI

https://www.repository.cam.ac.uk/handle/1810/256339

Repository DOI

https://doi.org/10.17863/CAM.282
Thumbnail Image

Files

tutorial-ende-wmt15-2.tar.gz (1.52 GB)

Type

Dataset

Change log

Authors

Stahlberg, Felix  ORCID logo  https://orcid.org/0000-0002-0430-5704

Description

The data set includes two NMT models trained on the English-German WMT'15 parallel data, a German NPLM language model, and an n-best list and translation lattices generated with HiFST for the WMT'15 test set. It is intended to support the tutorial for the SGNMT tool.

Version

Software / Usage instructions

SGNMT, Blocks, OpenFST, NPLM (see http://ucam-smt.github.io/sgnmt/html/setup.html)

Keywords

NMT, WMT'15, SGNMT, English, German

Publisher

University of Cambridge

Rights and licensing

Attribution-ShareAlike 4.0 International
Except where otherwised noted, this item's license is described as Attribution-ShareAlike 4.0 International
Sponsorship
EPSRC (EP/L027623/1)

Relationships

Supplements:
https://doi.org/10.18653/v1/P16-2049
Dataset:
Training data: http://www.statmt.org/wmt15/
Webpage:
Tutorial page: http://ucam-smt.github.io/sgnmt/html/tutorial.html

Collections

Research Data - Engineering
Symplectic mapped items for data match