blob: a3d54ffcf67b261e05ca6ae61632ac82e852a87d (
plain)
1
2
3
|
557 ./cdec_extools/extractor -i btec/split.zh-en.al -c 500000 -L 12 -C | sort -t $'\t' -k 1 | ./cdec_extools/mr_stripe_rule_reduce > btec.concordance
559 wc -l btec.concordance
588 cat btec.concordance | sed 's/.* //' | awk '{ for (i=1; i < NF; i++) { x=substr($i, 1, 2); if (x == "C=") printf "\n"; else if (x != "||") printf "%s ", $i; }; printf "\n"; }' | sort | uniq | wc -l
|
