資源簡介
BIO標注集,即B-PER、I-PER代表人名首字、人名非首字,B-LOC、I-LOC代表地名首字、地名非首字,B-ORG、I-ORG代表組織機構名首字、組織機構名非首字,O代表該字不屬于命名實體的一部分。

代碼片段和文件信息
#?Python?version?of?the?evaluation?script?from?CoNLL‘00-
#?Originates?from:?https://github.com/spyysalo/conlleval.py
#?Intentional?differences:
#?-?accept?any?space?as?delimiter?by?default
#?-?optional?file?argument?(default?STDIN)
#?-?option?to?set?boundary?(-b?argument)
#?-?LaTeX?output?(-l?argument)?not?supported
#?-?raw?tags?(-r?argument)?not?supported
import?sys
import?re
import?codecs
from?collections?import?defaultdict?namedtuple
ANY_SPACE?=?‘‘
class?FormatError(Exception):
????pass
Metrics?=?namedtuple(‘Metrics‘?‘tp?fp?fn?prec?rec?fscore‘)
class?EvalCounts(object):
????def?__init__(self):
????????self.correct_chunk?=?0????#?number?of?correctly?identified?chunks
????????self.correct_tags?=?0?????#?number?of?correct?chunk?tags
????????self.found_correct?=?0????#?number?of?chunks?in?corpus
????????self.found_guessed?=?0????#?number?of?identified?chunks
????????self.token_counter?=?0????#?token?counter?(ignores?sentence?breaks)
????????#?counts?by?type
????????self.t_correct_chunk?=?defaultdict(int)
????????self.t_found_correct?=?defaultdict(int)
????????self.t_found_guessed?=?defaultdict(int)
def?parse_args(argv):
????import?argparse
????parser?=?argparse.ArgumentParser(
????????description=‘evaluate?tagging?results?using?CoNLL?criteria‘
????????formatter_class=argparse.ArgumentDefaultsHelpFormatter
????)
????arg?=?parser.add_argument
????arg(‘-b‘?‘--boundary‘?metavar=‘STR‘?default=‘-X-‘
????????help=‘sentence?boundary‘)
????arg(‘-d‘?‘--delimiter‘?metavar=‘CHAR‘?default=ANY_SPACE
????????help=‘character?delimiting?items?in?input‘)
????arg(‘-o‘?‘--otag‘?metavar=‘CHAR‘?default=‘O‘
????????help=‘alternative?outside?tag‘)
????arg(‘file‘?nargs=‘?‘?default=None)
????return?parser.parse_args(argv)
def?parse_tag(t):
????m?=?re.match(r‘^([^-]*)-(.*)$‘?t)
????return?m.groups()?if?m?else?(t?‘‘)
def?evaluate(iterable?options=None):
????if?options?is?None:
????????options?=?parse_args([])????#?use?defaults
????counts?=?EvalCounts()
????num_features?=?None???????#?number?of?features?per?line
????in_correct?=?False????????#?currently?processed?chunks?is?correct?until?now
????last_correct?=?‘O‘????????#?previous?chunk?tag?in?corpus
????last_correct_type?=?‘‘????#?type?of?previously?identified?chunk?tag
????last_guessed?=?‘O‘????????#?previously?identified?chunk?tag
????last_guessed_type?=?‘‘????#?type?of?previous?chunk?tag?in?corpus
????for?line?in?iterable:
????????line?=?line.rstrip(‘\r\n‘)
????????if?options.delimiter?==?ANY_SPACE:
????????????features?=?line.split()
????????else:
????????????features?=?line.split(options.delimiter)
????????if?num_features?is?None:
????????????num_features?=?len(features)
????????elif?num_features?!=?len(features)?and?len(features)?!=?0:
????????????raise?FormatError(‘unexpected?number?of?features:?%d?(%d)‘?%
??????????????????????????????(len(features)?num_features))
????????if?len(features)?==?0?or?features[0]?==?options.boundary:
????????????features?=?[options.boundary
?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????文件??????12728??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\conlleval
?????文件??????10110??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\conlleval.py
?????文件??????10110??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\data\conlleval.py
?????文件????1383712??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\data\example.dev
?????文件????1405788??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\data\example.test
?????文件????5596172??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\data\example.train
?????文件???????8104??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\data_utils.py
?????文件???????5782??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\loader.py
?????文件???????8918??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\main.py
?????文件??????11605??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\model.py
?????文件???????1273??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\README.md
?????文件???????9470??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\rnncell.py
?????文件???????6038??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\utils.py
?????文件???15335492??2017-07-05?00:18??ChineseNER-master(來源聯合數據)\wiki_100.utf8
?????目錄??????????0??2018-08-06?17:18??ChineseNER-master(來源聯合數據)\data
?????目錄??????????0??2018-08-06?17:19??ChineseNER-master(來源聯合數據)
-----------?---------??----------?-----??----
?????????????23805302????????????????????16
- 上一篇:OpenGL實踐三:水面漣漪的逼真繪制畢業設計
- 下一篇:廣工計算機組成原理實驗報告
評論
共有 條評論