Project
Jeopardy! Question Answering Bot
Challenging
26 completions
~ 29 hours
4.6While creating a question-answering bot, you will learn how to use sentence embedding algorithms to separate user questions. You will also will learn more about preparing a corpus for creating a QA system.
Provided by
JetBrains Academy
About
Create a bot that can answer questions in different fields of knowledge, using the Jeopardy! question-answering database. In 2011, IBM Watson beat people at this game. Can your QA bot do better?
Graduate project
This project covers the core topics of the Chatbots with Python course, making it sufficiently challenging to be a proud addition to your portfolio.
At least one graduate project is required to complete the course.
What you'll learn
Once you choose a project, we'll provide you with a study plan that includes all the necessary topics from your course to get it built. Here’s what awaits you:
Teach your bot to introduce itself and ask a user for their question.
Preprocess the training corpus and a user's request. Tokenize the texts and remove the punctuation.
Train the Doc2Vec model on the preprocessed corpus and feed user questions to the model. The bot will print the number of the closest topic and similarity percentage.
Let the bot choose a response to the question from the answer table and print it.
Reviews
AM
Anastasiya Mostovaya4 months ago
Great course! Clear structure, fun hands-on projects, and a perfect intro to NLP and machine learning. Learned a lot!
11 months ago
Apart from some confusion on where to download the JSON file, great project!
2 years ago
The most important NLP models for working with text. The project has problems with theory and study plan, but the practical part is excellent)
4.6
Learners who completed this project within the Chatbots with Python course rated it as follows: