Skip to content

Latest commit

 

History

History
68 lines (68 loc) · 9.54 KB

DATASETS.md

File metadata and controls

68 lines (68 loc) · 9.54 KB
Dataset Description
mtedx/valid mTEDx evaluation data, valid: URL
mtedx/test mTEDx evaluation data, test: URL
wmt23 Official evaluation and system data for WMT23.
wmt22 Official evaluation and system data for WMT22.
wmt21/systems WMT21 system output.
wmt21/dev Development data for WMT21,if multiple references are available, the first one is used.
wmt21/D Official evaluation data for WMT21 with reference D
wmt21/C Official evaluation data for WMT21 with reference C
wmt21/B Official evaluation data for WMT21 with reference B.
wmt21/AC Official evaluation data for WMT21 with references A and C
wmt21/AB Official evaluation data for WMT21 with references A and B.
wmt21 Official evaluation data for WMT21.
wmt20/robust/set1 WMT20 robustness task, set 1
wmt20/robust/set2 WMT20 robustness task, set 2
wmt20/robust/set3 WMT20 robustness task, set 3
wmt20/tworefs WMT20 news test sets with two references
wmt20 Official evaluation data for WMT20
mtnt2019 Test set for the WMT 19 robustness shared task
mtnt1.1/test Test data for the Machine Translation of Noisy Text task: URL
mtnt1.1/valid Validation data for the Machine Translation of Noisy Text task: URL
mtnt1.1/train Training data for the Machine Translation of Noisy Text task: URL
wmt20/dev Development data for tasks new to 2020.
wmt19 Official evaluation data.
wmt19/dev Development data for tasks new to 2019.
wmt19/google/ar Additional high-quality reference for WMT19/en-de.
wmt19/google/arp Additional paraphrase of wmt19/google/ar.
wmt19/google/wmtp Additional paraphrase of the official WMT19 reference.
wmt19/google/hqr Best human selected-reference between wmt19 and wmt19/google/ar.
wmt19/google/hqp Best human-selected reference between wmt19/google/arp and wmt19/google/wmtp.
wmt19/google/hqall Best human-selected reference among original official reference and the Google reference and paraphrases.
wmt18 Official evaluation data.
wmt18/test-ts Official evaluation sources with extra test sets interleaved.
wmt18/dev Development data (Estonian<>English).
wmt17 Official evaluation data.
wmt17/B Additional reference for EN-FI and FI-EN.
wmt17/tworefs Systems with two references.
wmt17/improved Improved zh-en and en-zh translations.
wmt17/dev Development sets released for new languages in 2017.
wmt17/ms Additional Chinese-English references from Microsoft Research.
wmt16 Official evaluation data.
wmt16/B Additional reference for EN-FI.
wmt16/tworefs EN-FI with two references.
wmt16/dev Development sets released for new languages in 2016.
wmt15 Official evaluation data.
wmt14 Official evaluation data.
wmt14/full Evaluation data released after official evaluation for further research.
wmt13 Official evaluation data.
wmt12 Official evaluation data.
wmt11 Official evaluation data.
wmt10 Official evaluation data.
wmt09 Official evaluation data.
wmt08 Official evaluation data.
wmt08/nc Official evaluation data (news commentary).
wmt08/europarl Official evaluation data (Europarl).
iwslt17 Official evaluation data for IWSLT.
iwslt17/tst2016 Development data for IWSLT 2017.
iwslt17/tst2015 Development data for IWSLT 2017.
iwslt17/tst2014 Development data for IWSLT 2017.
iwslt17/tst2013 Development data for IWSLT 2017.
iwslt17/tst2012 Development data for IWSLT 2017.
iwslt17/tst2011 Development data for IWSLT 2017.
iwslt17/tst2010 Development data for IWSLT 2017.
iwslt17/dev2010 Development data for IWSLT 2017.
multi30k/2016 2016 flickr test set of Multi30k dataset
multi30k/2017 2017 flickr test set of Multi30k dataset
multi30k/2018 2018 flickr test set of Multi30k dataset. See URL for evaluation.