Dr. Watson: The Synonyms Game

From Master Projects
Jump to: navigation, search


has title::Dr. Watson: The Synonyms Game
status: finished
Student name: student name::Benjamin Timmermans
Dates
Start start date:=2014/01/01
End end date:=2014/07/01
Supervision
Supervisor: Lora Aroyo
Second supervisor: Robert-Jan Sips
Company: has company::IBM
Thesis: has thesis::Media:Thesis-design-B-Timmermans.pdf
Poster: has poster::Media:Presentation Thesis Design.pdf

Signature supervisor



..................................

Abstract

About Dr. Watson: The Synonyms Game

Description

IBM Research and the Cleveland Clinic are bringing IBM Watson to medical school to create a learning application for students. Watson will help students navigate medical information and make the best decisions. Students will also be able to teach and train Watson to advance its knowledge.

Read about IBM Watson going medical, and watch a video to learn about the context for this assignment.

This assignment will be done in the context of teaching and training Watson by using crowdsourcing and gaming strategies.

AI systems, such as IBM Watson, answer questions posed in natural language. For this they need to trained in understanding texts in natural language. Currently, Watson is being trained in medical domain, and one of the challenges is to learn how to LEARN SYNONYM PHRASES & TERMS.

In this MSc project you will explore the use of crowdsourcing and/or games with purpose for playfully learning medical terms and phrases and their synonym expressions.

The work on this Master's project is performed in collaboration with IBM Research, Chris Welty one of the developers of Watson, the IBM computer that defeated the best players on the American game show Jeopardy!.

Tasks

  • explore the domain of serious games and games with purpose
  • model the synonym matching scenario
  • identify gaming elements that are appropriate for this scenario
  • define game scenarios
  • evaluate and compare the game scenarios

Tools and Data

In this project you will be working with the following data:

  • medical sentences, where terms and phrases are identified
  • examples of games with purpose, e.g. DuoLingo
  • examples of active learning mechanisms, e.g. iPhoto face recognition feedback cycle

Recommended prior knowledge

  • Knowledge & Media course
  • Social Web course
  • Research methods course
  • Serious Games
  • Note: no medical knowledge is required for this assignment

Extra Information

Contact Lora_Aroyo, Michiel_Hildebrand or Guus_Schreiber for more information about this project.