How to build a chatbot that reads all your website data to find the right answer

  • A Retriever selects a set of candidate documents from all the available information. Among other options, we can rely on ElasticSearch to index the documents and return those that most likely contain the answer to the question
  • A Reader applies state-of-the-art QA models to try to infer an answer from each candidate

Creating the chatbot, the “front-end”

Loading the information to ElasticSearch

Finding the answer

But, does it work?

--

--

--

ICREA Research Professor at IN3 (UOC). Talking about software engineering, open source, AI and how the three of them can help each other.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

The Virtual Warehouse of scalable, unlimited resources! — Cloud Computing

Concurrency & Parallelism in Computing

Providing a better experience for .NET developers with Caller Argument Expressions

Taller Digital: Vectores en Illustrator

Data Warehouse Facts, Dimensions, and Star Schema

Repair a thin pool

Sorting Algorithm

Build a server for sending web push notifications

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Jordi Cabot

Jordi Cabot

ICREA Research Professor at IN3 (UOC). Talking about software engineering, open source, AI and how the three of them can help each other.

More from Medium

leturfu.fr, a 100% automated blog with NLP

How to build your own chatbot intent classifier

Learning Chatbot from Scratch: Rasa Open Source 3.x Installation and Set up on macOS

NLP BASED CHATBOTS