WMT2017 German-English machine translation challenge for news

Translate news articles from German into English. [ver. 1.0.0]

Log in to write a comment

[anonymized]   2021-02-17 19:16
submitted a solution:result
[anonymized]   2021-02-12 19:54
submitted a solution:notebook
[anonymized]   2021-02-12 19:53
submitted a solution:m2m-100
[anonymized]   2020-01-28 17:56
submitted a solution:translation with ready made fairseq transformer.wmt19.de-en v2
[anonymized]   2020-01-27 20:40
submitted a solution:translation with ready made fairseq transformer.wmt19.de-en
[anonymized]   2020-01-27 12:19
submitted a solution:CNN, sample_size = 5mln, epochs = 5
[anonymized]   2020-01-22 16:58
submitted a solution:Transformer, sample_size = 5mln, epochs = 2
[anonymized]   2020-01-22 15:00
submitted a solution:CNN, sample_size = 5mln, epochs = 7
[anonymized]   2020-01-21 23:23
submitted a solution:Transformer, sample_size = 5mln, epochs = 2
[anonymized]   2020-01-21 17:46
submitted a solution:CNN, sample_size = 5mln, epochs = 5
[anonymized]   2020-01-21 16:50
submitted a solution:CNN, sample_size = 5mln, epochs = 4
[anonymized]   2020-01-21 10:11
submitted a solution:CNN, sample_size = 0.5mln, epochs = 25
[anonymized]   2020-01-21 08:40
submitted a solution:CNN, sample_size = 0.5mln, epochs = 10
[anonymized]   2020-01-20 23:57
submitted a solution:CNN, sample_size = 1mln, epochs = 13
[anonymized]   2020-01-20 18:44
submitted a solution:Add files via upload
[anonymized]   2020-01-20 18:26
submitted a solution:Add files via upload
[anonymized]   2020-01-20 12:06
submitted a solution:CNN, sample_size = 1mln, epochs = 2
[anonymized]   2020-01-20 08:09
submitted a solution:Add files via upload
[anonymized]   2020-01-19 12:27
submitted a solution:CNN, sample_size = 0.5mln, epochs = 5
[anonymized]   2020-01-19 12:06
submitted a solution:Add files via upload
[anonymized]   2020-01-19 12:05
submitted a solution:Add files via upload
[anonymized]   2020-01-19 10:44
submitted a solution:Add files via upload
[anonymized]   2020-01-15 22:16
submitted a solution:Add files via upload
[anonymized]   2020-01-15 22:12
submitted a solution:Add files via upload
[anonymized]   2020-01-15 09:58
submitted a solution:Poprawienie Tokenizacji istniejacego rozwiazania v3
[anonymized]   2020-01-15 09:29
submitted a solution:Poprawienie Tokenizacji istniejacego rozwiazania v2
[anonymized]   2020-01-15 09:15
submitted a solution:Poprawienie Tokenizacji istniejacego rozwiazania
[anonymized]   2020-01-15 07:13
submitted a solution:convolutional nn
[anonymized]   2020-01-14 20:53
submitted a solution:fix tokenization of output
[anonymized]   2020-01-14 20:24
submitted a solution:Add files via upload
[anonymized]   2020-01-07 11:35
submitted a solution:ready-made Fairseq model
[anonymized]   2019-12-30 09:59
submitted a solution:Runed a ready-made Fairseq model
[anonymized]   2019-05-22 21:02
submitted a solution:marian 100k tg freq 10000
[anonymized]   2019-05-22 18:44
submitted a solution:marian 100k freq 10000
[anonymized]   2019-05-22 12:01
submitted a solution:marian 1M
[anonymized]   2019-05-22 11:47
submitted a solution:marian 1M tg
[anonymized]   2019-02-05 11:36
submitted a solution:type=s2s, corpseLen=1M, valid-freq 10000, early-stopping 5, workspace 2500, postproc sed deescapeSpecialChars detruecase awk sed
[anonymized]   2019-01-22 17:17
submitted a solution:type=amun, corpseLen=1M, valid-freq 10000, early-stopping 5, workspace 2500, postproc sed deescapeSpecialChars detruecase awk sed
[anonymized]   2019-01-12 12:57
submitted a solution:corpseLen=590k, valid-freq 10000, early-stopping 5, workspace 3000, postproc sed deescapeSpecialChars detruecase awk sed
[anonymized]   2019-01-12 11:20
submitted a solution:corpseLen=590k, valid-freq 10000, early-stopping 5, postproc sed deescapeSpecialChars detruecase awk
[anonymized]   2019-01-11 10:18
submitted a solution:corpseLen=590k, valid-freq 10000, early-stopping 5, postproc sed deescapeSpecialChars detruecase
[anonymized]   2019-01-11 10:08
submitted a solution:corpseLen=590k, valid-freq 10000, early-stopping 5, postproc sed deescapeSpecialChars
[anonymized]   2019-01-11 10:06
submitted a solution:corpseLen=590k, valid-freq 10000, early-stopping 5, postproc sed
[anonymized]   2019-01-11 09:58
submitted a solution:corpseLen=590k, valid-freq 10000, early-stopping 5, postproc sed
[anonymized]   2019-01-10 22:12
submitted a solution:corpseLen=590k, valid-freq 10000, early-stopping 5, no postproc
[anonymized]   2019-01-10 22:08
submitted a solution:corpseLen=590k, valid-freq 10000, early-stopping 5, no postproc
[anonymized]   2019-01-03 22:12
submitted a solution:with awk simple postproc on out
[anonymized]   2018-12-09 14:47
submitted a solution:Second dell commit
[anonymized]   2018-12-09 14:05
submitted a solution:First dell commit try
[anonymized]   2018-02-15 00:38
submitted a solution:Tensorflow 80k iterations ; beam 4 alpha 0.9
[anonymized]   2018-02-15 00:05
submitted a solution:Tensorflow 80k iterations ; beam 3 alpha 0.6
[anonymized]   2018-02-14 23:18
submitted a solution:Tensorflow 86k iterations ; beam 3 alpha 0.6
[anonymized]   2018-02-14 11:47
submitted a solution:Tensorflow 50k iterations ; beam 20 alpha 0.6
[anonymized]   2018-02-07 11:10
submitted a solution:Add 5G data
[anonymized]   2018-02-07 11:00
submitted a solution:Add 5G data
[anonymized]   2018-02-07 10:51
submitted a solution:improve solution -stack 155
[anonymized]   2018-02-07 10:47
submitted a solution:Improve sollution -stack 155
[anonymized]   2018-02-04 23:59
submitted a solution:'baseline'
[anonymized]   2018-01-31 11:43
submitted a solution:corpus=590616, NB_OF_EPOCHS=8, MAX_WORDS=46000
[anonymized]   2018-01-24 11:05
submitted a solution:improve solution
p/tlen   2018-01-17 06:46
submitted a solution:NMT with Marian, vocabulary=70K, epochs=7
[anonymized]   2018-01-16 18:36
submitted a solution:--search-algorithm 1 -s 2000 --cube-pruning-pop-limit 2000 --cube-pruning-diversity 100-b 0.1 --minimum-bayes-risk
p/tlen   2018-01-15 09:13
submitted a solution:NMT trained with Marian on 10%, 5 epochs, 40K dictionary
[anonymized]   2018-01-14 16:45
submitted a solution:'ibm
[anonymized]   2018-01-14 16:33
submitted a solution:ibm1
[anonymized]   2018-01-13 21:39
submitted a solution:Baseline 10%, stack 200 beam 0.1
[anonymized]   2018-01-13 21:22
submitted a solution:
[anonymized]   2018-01-13 19:21
submitted a solution:
[anonymized]   2018-01-13 19:12
submitted a solution:
p/tlen   2018-01-09 18:10
submitted a solution:WMT16 neural model (decoded with Amun) + de-escape apostrophes
p/tlen   2018-01-08 21:13
submitted a solution:neural model (decoded with Amun)
[anonymized]   2018-01-08 18:13
submitted a solution:
[anonymized]   2018-01-08 18:04
submitted a solution:
[anonymized]   2018-01-08 17:57
submitted a solution:TAU-2017-21 - improve solution by changing some decoding options: -stack 100
[anonymized]   2018-01-08 16:35
submitted a solution:TAU-2017-21 - improve solution by changing some decoding options: -stack 150
[anonymized]   2018-01-08 15:45
submitted a solution:TAU-2017-21 - improve solution by changing some decoding options: -stack 200
[anonymized]   2018-01-08 15:02
submitted a solution:TAU-2017-21 - improve solution by changing some decoding options: -stack 2000
[anonymized]   2018-01-08 14:58
submitted a solution:TAU-2017-21 - improve solution by changing some decoding options: -search-algorithm 1 -stack 2000 -cube-pruning-pop-limit 2000 -cube-pruning-diversity 500
[anonymized]   2018-01-07 21:47
submitted a solution:TAU-2017-21 - improve solution by changing some decoding options: -search-algorithm 1 -stack 2000
[anonymized]   2018-01-07 16:29
submitted a solution:TAU-2017-21 - improve solution by changing some decoding options: -beam-threshold 0.01
[anonymized]   2018-01-07 13:30
submitted a solution:TAU-2017-21 - improve solution by changing some decoding options: -stack 1000
[anonymized]   2018-01-07 13:25
submitted a solution:TAU-2017-21 - improve solution by changing some decoding options: -search-algorithm 1
[anonymized]   2018-01-03 14:57
submitted a solution:MERTed && --beam-thresholds
[anonymized]   2018-01-03 14:30
submitted a solution:TAU-2017-20 - check 6 values for maximum stack size; plot graphs for BLEU and decoding time
[anonymized]   2018-01-03 13:30
submitted a solution:improve solution search-algorithm 1 -s 0 --cube-pruning-pop-limit 5000 --cube-pruning-diversity 100
[anonymized]   2018-01-03 09:39
submitted a solution:improve solution search-algorithm 1 -s 0
[anonymized]   2018-01-03 00:06
submitted a solution:dev-0 dev-1 test-A -stack 1500
[anonymized]   2018-01-02 22:05
submitted a solution:test-A/out.tsv -stack 1500
[anonymized]   2018-01-02 20:30
submitted a solution:dev-0/out.tsv 0.2126 -stack 1500
[anonymized]   2018-01-02 18:18
submitted a solution:improve solution search-algorithm 1 -cube-pruning-pop-limit 2000 -s 2000
[anonymized]   2018-01-02 17:36
submitted a solution:improve solution search-algorithm 1 and beam-threshold 10
[anonymized]   2018-01-02 17:24
submitted a solution:improve solution search-algorithm 1 and beam-threshold 100
[anonymized]   2018-01-02 17:05
submitted a solution:improve solution search-algorithm 1 and beam-threshold 100
[anonymized]   2018-01-02 16:25
submitted a solution:--search-algorithm 1=cube pruning --stack 100
[anonymized]   2018-01-02 16:15
submitted a solution:--search-algorithm 0=normal stack -stack 100
[anonymized]   2018-01-02 16:00
submitted a solution:--search-algorithm 1=cube pruning
[anonymized]   2018-01-02 15:28
submitted a solution:default
[anonymized]   2018-01-02 11:29
submitted a solution:dev-0/out.tsv 0.1982 -stack 1500
[anonymized]   2018-01-01 16:01
submitted a solution:slightly improved -beam-threshold 0.25 -stack 152
[anonymized]   2018-01-01 14:12
submitted a solution:slightly improved -stack 154
[anonymized]   2018-01-01 12:22
submitted a solution:slightly improved -stack 152
[anonymized]   2017-12-31 10:12
submitted a solution:MERTed && --beam-threshold 0.0625
[anonymized]   2017-12-31 09:11
submitted a solution:MERTed && --beam-threshold 0.125
[anonymized]   2017-12-31 00:49
submitted a solution:MERTed && --beam-threshold 0.25
[anonymized]   2017-12-31 00:05
submitted a solution:MERTed && --beam-threshold 0.5
[anonymized]   2017-12-30 20:25
submitted a solution:MERTed && --beam-threshold 1
[anonymized]   2017-12-30 20:00
submitted a solution:MERTed && --beam-threshold 2
[anonymized]   2017-12-30 19:29
submitted a solution:MERTed && --beam-threshold 4
[anonymized]   2017-12-30 18:59
submitted a solution:MERTed && --beam-threshold 8
[anonymized]   2017-12-30 18:33
submitted a solution:MERTed && --beam-threshold 16
[anonymized]   2017-12-30 18:08
submitted a solution:MERTed && --beam-threshold 32
[anonymized]   2017-12-30 17:17
submitted a solution:MERTed && --beam-threshold 64
[anonymized]   2017-12-20 15:48
submitted a solution:
[anonymized]   2017-12-19 21:42
submitted a solution:
kaczla   2017-12-19 19:23
submitted a solution:Moses baseline on 10% utterances
kaczla   2017-12-19 19:07
submitted a solution:Moses baseline on 10% utterances (stack 400, search-algorithm 1 = cube pruning)
kaczla   2017-12-19 18:57
submitted a solution:Moses baseline on 10% utterances (search-algorithm 1 = cube pruning)
kaczla   2017-12-19 18:11
submitted a solution:Moses baseline on 10% utterances (stack 1000)
kaczla   2017-12-19 16:17
submitted a solution:Moses baseline on 10% utterances (stack 400)
[anonymized]   2017-12-06 12:05
submitted a solution:TAU-2017-16 - baseline with the probing multiplier parameter p in build_binary program changed
[anonymized]   2017-12-05 20:10
submitted a solution:Add 5G monolingual data + MERT v2
[anonymized]   2017-12-04 13:57
submitted a solution:Add 5G monolingual data + MERT v1
[anonymized]   2017-11-30 18:42
submitted a solution:TAU-2017-06 - add dictionary extracted from dict.cc to corpus only; clean corpus
[anonymized]   2017-11-29 14:02
submitted a solution:Mert - part of training set
[anonymized]   2017-11-29 12:57
submitted a solution:TAU-2017-06 - add dictionary extracted from dict.cc to corpus and model language
kaczla   2017-11-29 11:57
submitted a solution:Moses baseline on 10% utterances (6-gram model)
kaczla   2017-11-29 11:54
submitted a solution:Moses baseline on 10% utterances (6-gram model)
kaczla   2017-11-29 11:50
submitted a solution:Moses baseline on 10% utterances (5-gram model - trie data structure)
kaczla   2017-11-29 11:48
submitted a solution:Moses baseline on 10% utterances
kaczla   2017-11-29 11:40
submitted a solution:baseline Moses on 100% utterances + 40GB english monolingual data (4-gram + pruning) - without mert
kaczla   2017-11-29 11:37
submitted a solution:baseline Moses on 100% utterances + 40GB english monolingual data (4-gram + pruning + 2 iteration MERT)
kaczla   2017-11-29 11:33
submitted a solution:baseline Moses on 100% utterances + 40GB english monolingual data (4-gram + pruning + 9 iteration MERT - weights no change)
[anonymized]   2017-11-26 09:13
submitted a solution:5G monolingual data
[anonymized]   2017-11-24 15:45
submitted a solution:used MERT (tuned and tested on dev-0)
[anonymized]   2017-11-24 15:39
submitted a solution:used MERT (tuned and tested on dev-0)
[anonymized]   2017-11-24 15:30
submitted a solution:used MERT (tuned and tested on dev-0)
[anonymized]   2017-11-22 15:41
submitted a solution:Portuguese-english translation (+ dictionary improvement)
[anonymized]   2017-11-22 15:05
submitted a solution:40GB language model
kaczla   2017-11-22 12:19
submitted a solution:baseline Moses on 100% utterances + 40GB english monolingual data (4-gram + pruning + 2 iteration MERT) - without dev-1
[anonymized]   2017-11-22 09:06
submitted a solution:Added 40GB corpora
[anonymized]   2017-11-21 16:36
submitted a solution:5G LM
[anonymized]   2017-11-21 13:39
submitted a solution:Add 5G monolingual data
[anonymized]   2017-11-20 19:31
submitted a solution:5G LM data
[anonymized]   2017-11-19 19:27
submitted a solution:test
[anonymized]   2017-11-16 14:35
submitted a solution:used MERT (tuned and tested on dev-0)
kaczla   2017-11-15 11:27
submitted a solution:baseline Moses on 10% utterances + 40GB english monolingual data
[anonymized]   2017-11-14 23:50
submitted a solution:Use 10%, split compounds
[anonymized]   2017-11-14 20:57
submitted a solution:Moses baseline on 10% utterances v2
[anonymized]   2017-11-14 20:02
submitted a solution:Moses baseline on 10% utterances
[anonymized]   2017-11-13 19:22
submitted a solution:MERT tune on a part of training set attempt 2
[anonymized]   2017-11-08 12:52
submitted a solution:Split compound nouns
[anonymized]   2017-11-08 01:24
submitted a solution:Moses
[anonymized]   2017-11-07 22:37
submitted a solution:Moses 100% utterances compact phrase and lexical-tables
[anonymized]   2017-11-07 21:26
submitted a solution:Merge branch 'master' of ssh://gonito.net/siulkilulki/wmt-2017
[anonymized]   2017-11-07 18:36
submitted a solution:MERT tune one a part of training set
kaczla   2017-11-07 17:40
submitted a solution:baseline Moses on 10% utterances + Wikipedia title (with identical titles) and Wiktionary (all translation)
kaczla   2017-11-06 21:05
submitted a solution:baseline Moses on 10% utterances + Wiktionary (all translation)
kaczla   2017-11-06 18:17
submitted a solution:baseline Moses on 10% utterances + Wiktionary (only first translation)
kaczla   2017-11-02 12:49
submitted a solution:baseline Moses on 10% utterances + Wikipedia title (with identical titles)
kaczla   2017-11-02 07:28
submitted a solution:baseline Moses on 10% utterances + Wikipedia title (ignore identical titles)
kaczla   2017-10-22 20:13
submitted a solution:Moses baseline on 50% utterances
kaczla   2017-10-21 07:58
submitted a solution:Add script for counting words
[anonymized]   2017-10-11 17:56
submitted a solution:Hope better solution
[anonymized]   2017-10-11 16:19
submitted a solution:my copy-solution
[anonymized]   2017-10-11 13:15
submitted a solution:my brilliant solution2
[anonymized]   2017-10-11 13:05
submitted a solution:my brilliant solution2
[anonymized]   2017-10-11 12:49
submitted a solution:TAU-2017-01 solution 01
kaczla   2017-10-11 11:12
submitted a solution:Popular german words
[anonymized]   2017-10-11 07:48
submitted a solution:my brilliant solution
kaczla   2017-10-11 05:40
submitted a solution:Popular english words
kaczla   2017-10-11 05:36
submitted a solution:Popular english words
p/tlen   2017-10-11 05:23
submitted a solution:Moses baseline on 10% utterances
p/tlen   2017-10-11 05:13
submitted a solution:baseline Moses on 10% utterances
kaczla   2017-10-11 05:11
submitted a solution:Popular english words
kaczla   2017-10-11 05:05
submitted a solution:Popular german words
[anonymized]   2017-10-10 19:39
submitted a solution:translated days
[anonymized]   2017-10-09 20:42
submitted a solution:test
[anonymized]   2017-10-09 20:40
submitted a solution:empty output
[anonymized]   2017-10-09 09:43
submitted a solution:my stupid solution
[anonymized]   2017-10-08 17:10
submitted a solution:[ ]
p/tlen   2017-10-05 06:07
Fixed empty output bug in BLEU
p/tlen   2017-10-05 06:04
submitted a solution:empty output
[anonymized]   2017-10-04 15:04
submitted a solution:stupid
[anonymized]   2017-10-04 14:46
submitted a solution:stupid solution 2
[anonymized]   2017-10-04 14:42
submitted a solution:stupid solution
[anonymized]   2017-10-03 13:23
submitted a solution:just checkin'