CS-Notes-byCKL
Primary version
Distributed SystemsInformation Retrieval Systeme ProjektPrimary version
Primary version
Distributed SystemsInformation Retrieval Systeme ProjektPrimary version
  • First Page
  • PHP Notes
    • How a Theme Is build
  • Applied Machine Vision
    • The Pinhole Camera Model
    • Linear Algebra Recap
  • NLU/NLP Chatbot powerd by Rasa for Telekom
    • RASA
      • Terminology and Definitions and structure of a bot
      • Rasa Core Vs Rasa NLU
      • Rasa NLU
        • Training and Data Format RASA NLU
        • Entity Extraction
        • Evaluation
      • Preprocessing Methods
        • Bag of Words
      • Setup
  • Evalutation/Testing
  • Distributed Sytems
    • Week 1
    • Java I/O
  • Diskrete Strukturen
    • 1. Kombinatorik
      • Kombinatorische Beweisprinzipien
      • Ziehen von Elementen aus einer Menge
      • Wichtige Zählprobleme
      • Rekursionsgleichungen
    • 2. Zahlentheorie
      • Teilbarkeit und Primzahlen
      • Modulare Arithmetik
      • Vermischtes
    • MIT Week 1 Proofs
    • 3. Graphentheorie
      • Modellieren von Graphen
      • Grundbegriffe
      • Bäume und Wälder
      • Graphen Eigenschaften
    • 4. Algebraische Strukturen
      • Verbände
      • Isomorphe und homomorphe Abbildungen
  • Fingerprint extraction of electrical appliances
    • 1. Data Preprocessing
    • 2. Transition Detection
  • AI in a nutshell
Powered by GitBook
On this page
  • 1. Define a domain:
  • 2. Define interpreter / NLU
  • 3. Chat with the bot !
  • Custom Actions :
  1. NLU/NLP Chatbot powerd by Rasa for Telekom
  2. RASA

Terminology and Definitions and structure of a bot

Source : https://core.rasa.com/tutorial_basics.html#tutorial-basics

1. Define a domain:

  • Domain : Defines the universe, the bots lifes in, consists of Intent, actions, templates, Slots, Entities

  • Intents : Things we expect users to say / request from the bot

  • Actions : Things the bot can do and say

  • Templates : template strings for the things your bot can say

  • Slots : information to keep track of during a conversation (e.g. a users age), can update during conversation

  • Entities : Pieces of information extracted form Text

  • Slots : store information like

  • Stories : Chat scenarios the bot can learn actions from

Rasa uses the Intent and the entities, to find the most fitting action to execute.

2. Define interpreter / NLU

  1. An interpreter performs Natural Language Understanding, by parsing incoming messages. We define the data in data/NLU.md .

  2. We need to define the configurartion of the NLU Model , which has the attributes pipeline, path, data .

3. Chat with the bot !

Custom Actions :

PreviousRASANextRasa Core Vs Rasa NLU

Last updated 6 years ago