blob: cd0f9d65cffe9c2868be0f285400229e60bfe047 (
plain)
1
2
3
4
5
6
7
8
9
|
# THIS FILE GIVES THE LOCATIONS OF THE CORPORA USED
# name path aligned-corpus LM xfeats.grammar dev dev-refs test1 testt-eval.sh ...
btec /export/ws10smt/data/btec/ split.zh-en.al lm/en.3gram.lm.gz xgrammar/grammar.gz devtest/devset1_2.zh devtest/devset1_2.lc.en* devtest/devset3.zh eval-devset3.sh
fbis /export/ws10smt/data/chinese-english.fbis corpus.zh-en.al
zhen /export/ws10smt/data/chinese-english corpus.zh-en.al
aren /export/ws10smt/data/arabic-english corpus.ar-en.al
uren /export/ws10smt/data/urdu-english corpus.ur-en.al
nlfr /export/ws10smt/data/dutch-french corpus.nl-fr.al
|
