| #corpus name : list of factors in corpus : [input] factor LMfilename, factor LMfilename, ... : [output] factor LMfilename, factor LMfilename, ... | |
| #(the given factors should be present in all files for the given corpus) | |
| devtest2006.de-en : surf pos lemma : surf europarl.de.srilm.gz : surf europarl.en.srilm.gz | |
| devtest2006.en-de : surf pos lemma : surf europarl.en.srilm.gz : surf europarl.de.srilm.gz | |
| test2006.en-de : surf : surf europarl.en.srilm.gz : surf europarl.de.srilm.gz | |
| #pstem: lemmas come from the Porter stemmer (and so are really a mix of stems and lemmas) | |
| pstem_devtest2006.de-en : surf pos lemma : : surf europarl.en.srilm.gz | |
| #replace esset with ss in German text | |
| ss_devtest2006.en-de : surf pos lemma : surf europarl.en.srilm.gz : surf ss_europarl.de.srilm.gz | |