Fill-in-the-blank¶
Fill-in-the-blank related modeling class
-
class
pororo.tasks.fill_in_the_blank.
PororoBlankFactory
(task: str, lang: str, model: Optional[str])[source]¶ Bases:
pororo.tasks.utils.base.PororoFactoryBase
Conduct fill-in-the-blank with one __ token
English (roberta.base.en)
dataset: N/A
metric: N/A
Korean (posbert.base.ko)
dataset: N/A
metric: N/A
Japanese (jaberta.base.ja)
dataset: N/A
metric: N/A
Chinese (zhberta.base.zh)
dataset: N/A
metric: N/A
- Parameters
sent (str) – input sentence which contains one __ token
- Returns
token candidates could be fitted into __ token
- Return type
List[str]
Examples
>>> fib = Pororo(task="fib", lang="en") >>> fib("David Beckham is a famous __ player.") ['football', 'soccer', 'basketball', 'baseball', 'sports'] >>> fib = Pororo(task="fib", lang="ko") >>> fib("손흥민은 __의 축구선수이다.") ['대한민국', '잉글랜드', '독일', '스웨덴', '네덜란드', '덴마크', '미국', '웨일스', '노르웨이', '벨기에', '프랑스', '국적', '일본', '한국'] >>> fib = Pororo(task="fib", lang="ja") >>> fib("日本の首都は__である。") ['東京', '大阪', '仙台', '釧路', '北海道'] >>> fib = Pororo(task="fib", lang="zh") >>> fib("三__男子在街上做同样的舞蹈。") ['个', '名', '位', '女', '组']