MCPcopy Create free account

hub / github.com/Clearailhc/ACE2005-toolkit / functions

Functions41 in github.com/Clearailhc/ACE2005-toolkit

↓ 7 callersMethodread
Load text in the given format (conllu|horizontal|vertical) and return list of ufal.udpipe.Sentence-s.
udpipe.py:22
↓ 6 callersMethodwrite
Write given ufal.udpipe.Sentence-s in the required format (conllu|horizontal|vertical).
udpipe.py:51
↓ 3 callersFunctioncompare_string_without_space
(src_words, tgt_words, ignore_punc=False)
extract.py:80
↓ 3 callersFunctionfind_span_offset
(sentences, text, text_start, text_end, model, lang)
extract.py:89
↓ 3 callersFunctionmodify_files
(opt, split)
extract.py:533
↓ 3 callersFunctionprocess_data
(opt, model, filenames, split)
format.py:94
↓ 3 callersFunctionread_files
(split)
format.py:43
↓ 3 callersMethodtokenize
Tokenize the text and return list of ufal.udpipe.Sentence-s.
udpipe.py:15
↓ 2 callersMethod_read
(self, text, input_format)
udpipe.py:29
↓ 2 callersFunctionfind_subspan_offset
(sent, offset, text, text_start, text_end, model)
extract.py:229
↓ 2 callersFunctionload_file_list
(language='en', name='train')
transform.py:13
↓ 2 callersMethodparse
Parse the given ufal.udpipe.Sentence (inplace).
udpipe.py:47
↓ 1 callersFunctioncheck_duplicate_files
(train, dev, test)
format.py:25
↓ 1 callersFunctioncorrect_entities
(list_of_entity, sentences, lang, model)
extract.py:342
↓ 1 callersFunctioncorrect_events
(list_of_events, list_of_entities, sentences, lang, model)
extract.py:426
↓ 1 callersFunctioncorrect_relations
(list_of_relations, list_of_entities, sentences, lang, model)
extract.py:493
↓ 1 callersFunctiondata_split
(all_data, rate=[0.8, 0.1, 0.1])
transform.py:143
↓ 1 callersFunctionget_BIO
(path, type_name, save=False)
build_BIO.py:107
↓ 1 callersFunctionget_entity_tag
get entity_tag for each token from data (not BIO type)
build_BIO.py:16
↓ 1 callersFunctionget_event_tag
(raw_data)
build_BIO.py:54
↓ 1 callersFunctionget_file_names
(dirpath)
extract.py:23
↓ 1 callersFunctionget_filenames
Check if file exists, return a file list for train/dev/test split.
format.py:40
↓ 1 callersFunctionget_sentence_token
get sentences token from data
build_BIO.py:8
↓ 1 callersFunctionload_conllu
(conllu_file)
extract.py:37
↓ 1 callersFunctionload_json
(json_file)
extract.py:31
↓ 1 callersFunctionload_processed_data
(file_list, language='English', name='train')
transform.py:23
↓ 1 callersFunctionmain
(args)
format.py:132
↓ 1 callersFunctionmain
(args)
extract.py:584
↓ 1 callersMethodparse_entity_tag
(node)
ace_parser.py:25
↓ 1 callersMethodparse_event_tag
(node)
ace_parser.py:79
↓ 1 callersMethodparse_relation_tag
(node)
ace_parser.py:49
↓ 1 callersFunctionparse_sgm
(model, sgm_path)
format.py:69
↓ 1 callersMethodparse_value_timex_tag
(node)
ace_parser.py:111
↓ 1 callersFunctionparse_xml
(xml_path)
format.py:85
↓ 1 callersMethodparse_xml
(self, xml_path)
ace_parser.py:11
↓ 1 callersFunctionprint_count
(data)
transform.py:127
↓ 1 callersFunctionsave_data
(data, path)
transform.py:122
↓ 1 callersMethodtag
Tag the given ufal.udpipe.Sentence (inplace).
udpipe.py:43
Method__init__
(self, path)
ace_parser.py:5
Method__init__
Load given model.
udpipe.py:9
Functioncount_type
统计每个事件类型的数目
transform.py:72