Logo Questions Linux Laravel Mysql Ubuntu Git Menu
 

What is the algorithm behind Rasa NLU?

Tags:

rasa-nlu

nlu

rasa

I see the Rasa NLU use the MITIE and spaCy, but can anyone explain the how they use it and the algorithm behind?

like image 829
Gary Ng Avatar asked Feb 21 '18 02:02

Gary Ng


People also ask

What algorithm does Rasa use?

The algorithm is built through a comprehensive study and analysis of two well known task scheduling algorithms, Min-min and Max-min. RASA uses the advantages of the both algorithms and covers their disadvantages.

What algorithm is used in Rasa chatbot?

RASA machine learning framework consists of two main components. First one being the Rasa NLU (Natural language understanding) and Rasa Core (Dialogue management) model being the second one. NLU model is an algorithm that helps us to train our assistant to learn the meaning of words and intention behind them.

How does NLU work in Rasa?

Rasa NLU examines the user's input, classifies the intent, and extracts the entities. Rasa core takes the user's input and generates a response accordingly using various pipelines. Rasa is an effective and time-efficient tool to build complex chatbots and works out of the box in dialogue management.

What is Rasa NLU model?

Rasa is a tool to build custom AI chatbots using Python and natural language understanding (NLU). Rasa provides a framework for developing AI chatbots that uses natural language understanding (NLU). It also allows the user to train the model and add custom actions.


2 Answers

There is a post by Alan on the Rasa blog here that covers the basic approach used: https://medium.com/rasa-blog/do-it-yourself-nlp-for-bot-developers-2e2da2817f3d

This should give a good idea of roughly what it's doing but if you are keen to find out more, you can easily look over the actual code used (which is the great advantage of open source solutions!) https://github.com/RasaHQ/rasa_nlu/tree/master/rasa_nlu

like image 53
Neil Avatar answered Sep 28 '22 00:09

Neil


It depends what kind of NER you want to use for your bot.. basically you define a pipeline in your configuration file ... most preferred is spacy since its corpus is being updated regularly and widely used .. mitie is not that good as compare to spacy and also is an older version.

language: "en"

pipeline: "spacy_sklearn"

you can read in more details here : choosing rasa nlu pipeline

like image 45
ajay kumar prajapati Avatar answered Sep 28 '22 00:09

ajay kumar prajapati