3

I am trying to build a chatbot using Rasa. I have created a basic chatbot by following the steps given in documentation here. I have installed both rasa core and rasa nlu but for now i am using only rasa core as i don't need to extract any information from input.

I have added around 20 intents and their corresponding actions. But when i trying to get response it is recognising 14 intent accurately (tested even by jumbling word, by using synonyms) but for rest 6 intent it is always returning wrong response even if i enter same input as defined in intent.

At first i used spaCy + sklearn pipeline but now i am using sklearn + MITIE but still not getting accurate responses.

Is there any way to improve the accuracy of chatbot.

Henu
  • 1,622
  • 2
  • 22
  • 27
  • are you able to give some examples of utterances which are misclassified? It's hard to give any suggestions of how to improve performance without seeing some data. Please give examples of intents which work well and some which don't – amn41 Jan 08 '18 at 07:13
  • Hello @DarkShadow, can you solve this problem? I face same issue – Jignasha Royala Jan 17 '18 at 09:42
  • @jignasha No, I haven't figured out any way yet – Henu Jan 18 '18 at 04:56

1 Answers1

3

The best way to improve accuracy is to optimize your bot iteratively based on what conversational analytics tells you about how it interacts with users over time. It's unrealistic to expect a bot to be accurate out of the box, no matter how much NLP you bring to the table.

There are a bunch of tools available for this, with some being stronger in analytics (in addition to health metrics) than others. (I work for one called Chatbase, which is free to use and works with any bot platform.)

Justin Kestelyn
  • 924
  • 5
  • 12
  • 1
    Optimisation will be a thing to identify some modified intent. In my case, input is exactly same as added in domain.yml file but still rasa isn't identifying the correct intent. – Henu Jan 18 '18 at 05:05