diff --git a/UD_any/data/Makefile b/UD_any/data/Makefile index e869f10caa3a1113648e7d042f482c8f8a067837..f8896e0a90cb5ece636d7f42746c1da94c7475a4 100644 --- a/UD_any/data/Makefile +++ b/UD_any/data/Makefile @@ -38,7 +38,7 @@ tokenizer.ts: all_no_test.conllu segmenter.ts: echo "EOS b.0" > $@ - echo "NOTHING" >> $@ + echo "NOTEOS b.0" >> $@ sed -i -e 's/^/<segmenter> /' $@ transitions: all_no_test.conllu diff --git a/UD_any/data/getTransitionSets.py b/UD_any/data/getTransitionSets.py index 4a04170272dd2277083e70f35ba007028bfd4a0b..3145745f66e9ae80be547d5e743995f50d756b43 100755 --- a/UD_any/data/getTransitionSets.py +++ b/UD_any/data/getTransitionSets.py @@ -90,11 +90,11 @@ if __name__ == "__main__" : print("<lemmatizer_rules> TRANSFORMSUFFIX FORM b.0 LEMMA b.0 %s"%rule, file=output) output.close() output = open("lemmatizer_case.ts", 'w', encoding='utf-8') + print("<lemmatizer_case> NOTHING LEMMA b.0", file=output) print("<lemmatizer_case> UPPERCASEINDEX LEMMA b.0 0", file=output) print("<lemmatizer_case> UPPERCASE LEMMA b.0", file=output) print("<lemmatizer_case> LOWERCASEINDEX LEMMA b.0 0", file=output) print("<lemmatizer_case> LOWERCASE LEMMA b.0", file=output) - print("<lemmatizer_case> NOTHING", file=output) output.close() if "DEPREL" in col2index :