ArticutAPI Versions Save

API of Articut 中文斷詞 (兼具語意詞性標記):「斷詞」又稱「分詞」,是中文資訊處理的基礎。Articut 不用機器學習,不需資料模型,只用現代白話中文語法規則,即能達到 SIGHAN 2005 F1-measure 94% 以上,Recall 96% 以上的成績。

v1.1.8

2 years ago

Bug fixes

  • Fix LocalRE.py's Regex pattern (alleyPat and roomPat).

v1.1.6

2 years ago

Adding autoBreakBOOL in parse() function, default value is True.

This feature will automatically split your input TEXT into sub-strings shorter than 5000 characters in length. With a punctuation mark at the end, your input TEXT will not be lost. Meanwhile, Articut users don't need to worry about your long text that may cause 408 Request Timeout error.

v1.1.5

2 years ago

Bug fixes

  • fix extract_tags() with withWeight parameter.

v1.1.4

2 years ago

Bug fixes

  • fix LocalRE regex Pat
  • fix textrank and TF-IDF args topK

Function updates

  • NER/LawsToolkit/LocalRE's func is compatible with bulk_parse

v1.1.3

2 years ago

New Feature

  • Implement localRE (Taiwan Address)

v1.1.2

3 years ago

New features

  • NER MSRA (Microsoft Research Lab Asia).

Bug fixes

  • LawsToolkit not found.

v1.1.0

3 years ago

Release Note

v1.0.12

3 years ago

Bug fixes

  • Fix timeRef format error.

v1.0.11

3 years ago

Bug fixes

v1.0.10

3 years ago

Bug fixes

  • Fix getVerbStemLIST() return format.