Question Answering (WS2011/2012)

Automatic Question Answering (QA) has received researchers’ attention over the last decade. It aims to find a short answer string which exactly addresses the users' questions rather than overwhelm them with a large number of retrieved documents, which they must sort through to find the desired answer.

This goal is usually achieved using a combination of different techniques, including

• information retrieval
• information extraction
• natural language processing
• opinion mining.

In this seminar we will cover the most important components and techniques that are required for building a question answering system. In addition, the students will build a QA system that can answer questions from "Who wants to be a millionaire?".

More information can be found in the cource webpage at information systems research group.

• basic knowledge on information retrieval and machine learning

• Weekly seminars
• Literature review for QA systems
• Implementation of a simple QA system for anwering multi-choice questions
• Presentation

• Attending weekly seminars
• Reading of relevant literature for one of the QA components and giving an intermediate talk about the component
• Implementing one part of a simple question answering system for "Who wants to be a millionaire?"
• Presenting the final results of the implemented QA system

The first session in which we will propose the relevant topics will be on Monday, October 17th, 2011 at 15:15. Room: A 2-2

www.hpi.uni-potsdam.de/naumann/teaching/ws_1112/question_answering.html

13 L 1355

VT OSIS

2

3 (benotet)

2.11.2011

IT Systems Engineering (Master)

Vertiefungsgebiete

Seminar

Wahlfach

Information Systems, Multimedia & Visualization, Systems Integration