rasa无法检测到正则表达式的luis实体，列表类型

Question

我正在使用LUIS模型（导出为json文件）通过命令“ rasa train --out models \ test.tar.gz”来构建rasa_nlu

Luis模型具有类型为list和regex的实体，而rasa_nlu模型无法提取。

例如： LUIS实体名称：“动物” LUIS实体类型：“列表” 列表中的元素就像猫，狗等...

如果我显示“如何训练狗”之类的字符串？

我希望像LUIS一样将“ dog”映射到“ Animal”实体，但是rasa_nlu不会将“ dog”检测为实体，因为它的类型为“ list”。如果实体类型更改为“简单”，rasa_nlu会检测到狗并将其归类为“动物”实体类型

类似地，如果luis实体类型为用“ 0x [a-f，0-9] {8} / i”标识的正则表达式，则rasa_nlu无法检测到它。

在检测luis regex和列表实体类型时，rasa_nlu是否存在任何问题，或者我做错了什么？

下面是用于训练rasa的json文件的内容

{
  "luis_schema_version": "3.2.0",
  "versionId": "0.1",
  "name": "Test",
  "desc": "",
  "culture": "en-us",
  "tokenizerVersion": "1.0.0",
  "intents": [
    {
      "name": "error"
    },
    {
      "name": "None"
    },
    {
      "name": "wild"
    }
  ],
  "entities": [],
  "composites": [],
  "closedLists": [
    {
      "name": "animal",
      "subLists": [
        {
          "canonicalForm": "dog",
          "list": []
        },
        {
          "canonicalForm": "cat",
          "list": []
        }
      ],
      "roles": []
    }
  ],
  "patternAnyEntities": [],
  "regex_entities": [
    {
      "name": "ecode",
      "regexPattern": "0x[a-f,0-9]{8}",
      "roles": []
    }
  ],
  "prebuiltEntities": [],
  "model_features": [],
  "regex_features": [],
  "patterns": [],
  "utterances": [
    {
      "text": "error 0x80070055",
      "intent": "error",
      "entities": []
    },
    {
      "text": "error while browsing 0x90909090",
      "intent": "error",
      "entities": []
    },
    {
      "text": "how to train cat",
      "intent": "wild",
      "entities": []
    },
    {
      "text": "how to train dog",
      "intent": "wild",
      "entities": []
    }
  ],
  "settings": []
}

感谢您的帮助！