|Website deprecated and outdated. Click here for the new site.|
Dept. of Computer Sc. » Pattern Recognition » Courses » SS 18 » Seminar Automatic Question Answering Using IBM Watson [SemWatson]
Seminar Automatic Question Answering Using IBM Watson [SemWatson]
The seminar will focus on the IBM Watson technology that is being used to build question answering system. The Watson system is quite well known because it was the first system to beat two human experts in the American quiz show "Jeopardy!". In the seminar, we will investigate natural language processing techniques and the Watson API in particular. In order to bring this technology also into an applied context, IBM will provide us with access to an Watson Instance that can be used to build own question answering systems embedded into IBM's Bluemix Cloud Architecture. Registration for the class will occur in the first appointment.
Dates & Rooms:
Wednesday, 8:30 - 10:00; Room: 01.134
You can find the introductory slide via this link: Slides
Medical Assistant(Chest X-ray Image Classifier)
Group 2: Final Project
In this project, students used IBM Watson Visual Recognition API to develop an application in order to classify the lung diseases. They built a web application framework which classify all the chest X-ray images into 4 different categories of diseases. This application is easy to use and can increase the confidence of radiologists in terms of diagnosis and prognosis.
Final Presentation: Medical Assistant(Chest X-ray Image Classifier)
Stock Market Analysis
Group 3: Final Project
In this project, students used IBM watson conversation and other third party application to develop an application that can predict the stock market value and trend.
Final Presentation: Stock Market Prediction
Application Demo 1: Stock Market Prediction demo1
Application Demo 2: Stock Market Prediction demo2
Customer Feedback Analysis
Group 4: Final Project
In this project, students used the IBM Watson Tone Analyser API to evaluate the customer feedbacks on twitter. Given the increasing popularity of customer service dialogue on Twitter, analysis of conversation data is essential to understand trends in customer and agent behavior for the purpose of improving customer service interactions.
– Measure customer satisfaction
– Evaluate agent performance
– See how conversations start verses how they finish
Using “Customer Service Analyzer” we can analyze conversations
between customers and customer service agents.
Final Presentation: Customer Feedback Analysis
Application Demo: Customer Feedback Analysis Demo