diff --git a/prepare-dataset.sh b/prepare-dataset.sh old mode 100644 new mode 100755 index e368ef9..14a9aac --- a/prepare-dataset.sh +++ b/prepare-dataset.sh @@ -11,6 +11,7 @@ cut -f2 mt-summit-corpora/test/constrained-scenario-test.tsv > mt-summit-corpora cut -f2 mt-summit-corpora/test/general-scenario-test.tsv > mt-summit-corpora/test/general-scenario-test.pl cut -f1 mt-summit-corpora/test/general-scenario-test.tsv > mt-summit-corpora/test/general-scenario-test.en +rm mt-summit-corpora.tar.gz rm mt-summit-corpora/train/train.en-pl rm mt-summit-corpora/test/*.tsv rm mt-summit-corpora/dev/dev.en-pl diff --git a/prepare-gonito.sh b/prepare-gonito.sh new file mode 100755 index 0000000..0259f42 --- /dev/null +++ b/prepare-gonito.sh @@ -0,0 +1,39 @@ +#!/bin/bash + +tar xvf mt-summit-corpora.tar.gz >> /dev/null 2>&1 + +cut -f1 mt-summit-corpora/train/train.en-pl > mt-summit-corpora/train/train.en +cut -f2 mt-summit-corpora/train/train.en-pl > mt-summit-corpora/train/train.pl +cut -f1 mt-summit-corpora/dev/dev.en-pl > mt-summit-corpora/dev/dev.en +cut -f2 mt-summit-corpora/dev/dev.en-pl > mt-summit-corpora/dev/dev.pl +cut -f1 mt-summit-corpora/test/constrained-scenario-test.tsv > mt-summit-corpora/test/constrained-scenario-test.en +cut -f2 mt-summit-corpora/test/constrained-scenario-test.tsv > mt-summit-corpora/test/constrained-scenario-test.pl +cut -f2 mt-summit-corpora/test/general-scenario-test.tsv > mt-summit-corpora/test/general-scenario-test.pl +cut -f1 mt-summit-corpora/test/general-scenario-test.tsv > mt-summit-corpora/test/general-scenario-test.en + +rm mt-summit-corpora.tar.gz +rm mt-summit-corpora/train/train.en-pl +rm mt-summit-corpora/test/*.tsv +rm mt-summit-corpora/dev/dev.en-pl + +mv mt-summit-corpora/dev ./dev-0 +mv mt-summit-corpora/train ./train +mv mt-summit-corpora/test ./test-A +rm -r mt-summit-corpora + +mv dev-0/dev.en dev-0/in.tsv +mv dev-0/dev.pl dev-0/expected.tsv +mv train/train.en train/in.tsv +mv train/train.pl train/expected.tsv +cd train +tar -czf in.tar.gz in.tsv +tar -czf expected.tar.gz expected.tsv +rm expected.tsv +rm in.tsv +cd .. +mv test-A/general-scenario-test.en test-A/in.tsv +mv test-A/general-scenario-test.pl test-A/expected.tsv +mkdir test-B +mv test-A/constrained-scenario-test.en test-B/in.tsv +mv test-A/constrained-scenario-test.pl test-B/expected.tsv +mv kompendium.tsv glossary.tsv