FILE_MAP = {'strings-list': 'strings.txt', 'obeliks-tokenised': 'obeliks_raw.conllu', 'obeliks-tweaked': 'obeliks_tweaked.conllu', 'classla-parsed': 'classla_raw.conllu', 'classla-translated': 'classla_translated.conllu', 'structure-schema': 'structures.xsd', 'tei-initial': 'tei_initial.xml', 'tei-ids-collocation': 'tei_ids_collocations.xml', 'tei-ids-all': 'tei_ids_all.xml', 'collocations': 'collocation_matches.csv', 'collocation-mapper': 'mapper.csv', 'structures-old': 'structures_old.xml', 'structures-new': 'structures_new.xml', 'dictionary': 'dictionary.xml', 'dictionary-schema': 'monolingual_dictionaries.xsd' } NLP_CONFIG_MAP = { 'type': 'standard_jos', 'processors': 'tokenize,pos,lemma,depparse', 'tokenize_pretokenized': 'conllu', 'pos_use_lexicon': True, }