（七）RASA NLU实体提取器

PERSON People, including fictional.
NORP Nationalities or religious or political groups.
FAC Buildings, airports, highways, bridges, etc.
ORG Companies, agencies, institutions, etc.
GPE Countries, cities, states.
LOC Non-GPE locations, mountain ranges, bodies of water.
PRODUCT Objects, vehicles, foods, etc. (Not services.)
EVENT Named hurricanes, battles, wars, sports events, etc.
WORK_OF_ART Titles of books, songs, etc.
LAW Named documents made into laws.
LANGUAGE Any named language.
DATE Absolute or relative dates or periods.
TIME Times smaller than a day.
PERCENT Percentage, including ”%“.
MONEY Monetary values, including unit.
QUANTITY Measurements, as of weight or distance.
ORDINAL “first”, “second”, etc.
CARDINAL Numerals that do not fall under another type.

pipeline:
- name: "SpacyEntityExtractor"
  # dimensions to extract
  dimensions: ["PERSON", "LOC", "ORG", "PRODUCT"]

==============  ==========================================================================================
Feature Name    Description
==============  ==========================================================================================
low             Checks if the token is lower case.
upper           Checks if the token is upper case.
title           Checks if the token starts with an uppercase character and all remaining characters are
                lowercased.
digit           Checks if the token contains just digits.
prefix5         Take the first five characters of the token.
prefix2         Take the first two characters of the token.
suffix5         Take the last five characters of the token.
suffix3         Take the last three characters of the token.
suffix2         Take the last two characters of the token.
suffix1         Take the last character of the token.
pos             Take the Part-of-Speech tag of the token (``SpacyTokenizer`` required).
pos2            Take the first two characters of the Part-of-Speech tag of the token
                (``SpacyTokenizer`` required).
pattern         Take the patterns defined by ``RegexFeaturizer``.
bias            Add an additional "bias" feature to the list of features.
==============  ==========================================================================================

pipeline:
- name: "CRFEntityExtractor"
  # BILOU_flag determines whether to use BILOU tagging or not.
  "BILOU_flag": True
  # features to extract in the sliding window
  "features": [
    ["low", "title", "upper"],
    [
      "bias",
      "low",
      "prefix5",
      "prefix2",
      "suffix5",
      "suffix3",
      "suffix2",
      "upper",
      "title",
      "digit",
      "pattern",
    ],
    ["low", "title", "upper"],
  ]
  # The maximum number of iterations for optimization algorithms.
  "max_iterations": 50
  # weight of the L1 regularization
  "L1_c": 0.1
  # weight of the L2 regularization
  "L2_c": 0.1
  # Name of dense featurizers to use.
  # If list is empty all available dense features are used.
  "featurizers": []
  # Indicated whether a list of extracted entities should be split into individual entities for a given entity type
  "split_entities_by_comma":
      address: False
      email: True

pipeline:
- name: "DucklingHTTPExtractor"
  # url of the running duckling server
  url: "http://localhost:8000"
  # dimensions to extract
  dimensions: ["time", "number", "amount-of-money", "distance"]
  # allows you to configure the locale, by default the language is
  # used
  locale: "de_DE"
  # if not set the default timezone of Duckling is going to be used
  # needed to calculate dates from relative expressions like "tomorrow"
  timezone: "Europe/Berlin"
  # Timeout for receiving response from http url of the running duckling server
  # if not set the default timeout of duckling http url is set to 3 seconds.
  timeout : 3

    pipeline:
    - name: RegexEntityExtractor
      # text will be processed with case insensitive as default
      case_sensitive: False
      # use lookup tables to extract entities
      use_lookup_tables: True
      # use regexes to extract entities
      use_regexes: True
      # use match word boundaries for lookup table
      "use_word_boundaries": True

[
    {
      "text": "I moved to New York City",
      "intent": "inform_relocation",
      "entities": [{
        "value": "nyc",
        "start": 11,
        "end": 24,
        "entity": "city",
      }]
    },
    {
      "text": "I got a new flat in NYC.",
      "intent": "inform_relocation",
      "entities": [{
        "value": "nyc",
        "start": 20,
        "end": 23,
        "entity": "city",
      }]
    }
]