Need help for data training

Hi guys. i have a doubt about my training data. i am to create a nlu with multiple intents and i have a large amount of data for training so i prefer this config. `language: “en”


  • name: “WhitespaceTokenizer”
  • name: “RegexFeaturizer”
  • name: “deepPavlov.DeepPavlov”
  • name: “CRFEntityExtractor” features: [ [“low”, “title”, “upper”], [“bias”, “low”, “prefix5”, “prefix2”, “suffix5”, “suffix3”,“suffix2”, “upper”, “title”, “digit”, “pattern”], [“low”, “title”, “upper”] ]
  • name: “EntitySynonymMapper”
  • name: “CountVectorsFeaturizer”
  • name: “EmbeddingIntentClassifier”
  • name: “DucklingHTTPExtractor” url: http://rasa-support timezone: UTC dimensions:
    • time
    • number
    • amount-of-money
    • distance
    • ordinal


  • name: MemoizationPolicy
  • name: KerasPolicy
  • name: MappingPolicy`

my doubt is , as i have multiple intents few looks so similar just some key words differ, should i use those keywords as slots(Entity) for best usage of nlu recognization or should i use that as a normal text. which method will increase my acurracy and good matching. Thanks in advance.

hey @prasanth55555 could you please give some example about how two sentences seems similar but with different intent.

I think giving those keywords as entity doesn’t effect.

@capgos17 lets say for example i have two intents namely

intent: listVideoIntent

  • list all my videos
  • list all my dvd
  • list all my movies

intent: listAudioIntent

  • list all my musics
  • list all my music
  • list all my mp3

i have these kind of similar intents. i cant have these intents in same intent as well. so please suggest me a way for making the nlu to recognize the text well.

`thanks for your reply @capgos17

yes you are right There should be only one intent.

intent: listContent


  • dvd
  • mp4
  • mkv


  • music
  • mp3
  • musics

may I know why?

the server side program have been there already to support seperate intent format. so i cant modify that. and another nlu is using that.