0

我有一个 ENAMEX 格式的数据集，如下所示：

<ENAMEX TYPE="LOCATION">Italy</ENAMEX>'s business world was rocked by the announcement <TIMEX TYPE="DATE">last Thursday</TIMEX> that Mr. <ENAMEX TYPE=„PERSON">Verdi</ENAMEX> would leave his job as vicepresident of <ENAMEX TYPE="ORGANIZATION">Music Masters of Milan, Inc</ENAMEX> to become operations director of <ENAMEX TYPE="ORGANIZATION">Arthur Andersen</ENAMEX>.

我想把它改成 CoNLL 格式：

Italy  LOCATION
's  O
business O
world  O
was  O
rocked  O
by  O
the  O
announcement  O
last  DATE
Thursday  DATE
...
.  O

我怎样才能做到这一点？这种格式转换是否有标准脚本？

4

1 回答 1

0

我自己写了一个对我有用的，虽然在这里没有经过严格的测试：

from __future__ import unicode_literals
import os
from os import path
import re
import os
import re
import en_core_web_sm #spacy

# to convert formats such as <ENAMEX type="LOCATION">Italy</ENAMEX> is experiencing an economic boom.

def xml_iter(file_):
    with open(file_, 'r') as fin:
        for line in fin:
            yield line.strip()



def markupline2bio(line):
            #print(line.split('\t')[0])
        record = line.split('\t')[0]
        #print(record)
        #print(parse(record))
        #print(record[35:40], record[81:90])
        #tags = re.findall(r'<ENAMEX\s+TYPE=\"(.+?)\">(.+?)</ENAMEX>', record)
        prev_start = 0
        prev_end = 0
        all_tokens = []
        all_tags = []
        for f in re.finditer(r'<ENAMEX\s+TYPE=\"(.+?)\">(.+?)</ENAMEX>', record):
            #print(record[f.start(0):f.end(0)], f.start(0), f.end(0))
            annotations = re.findall(r'<ENAMEX\s+TYPE=\"(.+?)\">(.+?)</ENAMEX>', record[f.start(0):f.end(0)])
            before_text = record[prev_end:f.start(0)]
            prev_start, prev_end = f.start(0), f.end(0)
            for tok in nlp(before_text):
                if str(tok).strip():
                    all_tokens.append(tok)
                    all_tags.append('O')
            for phrasetag in annotations:
                tag, phrase = annotations[0]
                tokens = nlp(phrase)
                for entity_tok_index, tok in enumerate(tokens):
                    if str(tok).strip():
                        all_tokens.append(tok)
                        if entity_tok_index == 0:
                            all_tags.append("B-" + tag)
                        else:
                            all_tags.append("I-" + tag)
                    else:
                        entity_tok_index -= 1

        after_text = record[prev_end:]
        for tok in nlp(after_text):
            if str(tok).strip():
                all_tokens.append(tok)
                all_tags.append('O')
        return all_tokens, all_tags

if __name__ == '__main__':
    data_dir = './data/indonesian_bert_all/Indonesian/ner/'
    xml_iterator = xml_iter(os.path.join(data_dir, 'data_train_ugm.txt'))
    output_file = os.path.join(data_dir, 'data_train_ugm.bio')
    #nlp = spacy.load("en_core_web_sm")
    nlp = en_core_web_sm.load()
    with open(output_file, 'w') as fout:
        for i, line in enumerate(xml_iterator):
            if i > 10:
                #break
                pass
            all_tokens, all_tags = markupline2bio(line.strip())
            #print(all_tokens)
            #print(all_tags)
            #print(line)
            for tok, tag in zip(all_tokens, all_tags):
                #print(tok, tag)
                fout.write(str(tok) + '\t' + tag)
                fout.write('\n')
            fout.write('\n')
于 2020-05-18T01:30:44.527 回答