Knowledge Engineering for Question Answering Systems SS 2014

Knowledge Engineering for Question Answering Systems

In this seminar, we will get to know IBM's Question-Anwering-System "IBM Watson", which has won the American game show "Jeopardy!" in 2011 against two human champions. As a basis, we provide the following materials: the articles from a special issue of IBM Journal of Research and Development, and original slides from the IBM Watson Tutorial held in SS 2013.

The journal describes the inner workings of IBM's Question-Answering-System. The method uses and combines techniques from different fields of research, e.g. Computational linguistics, Information Retrieval, Knowledge Representation and Machine Learning.

In the seminar, we will look at articles that provide an in-depth description of the functionality of single components.

We expect students to present their material in a presentation of about 45 minutes (30 minutes presentation, 15 minutes questions). We highly recommend to also enrol in the project "Question Answering Systems Project: Semantic Technologies in IBM Watson", in order to transfer the theoretic knowledge from the seminar to practice.

Recommended:

  • Participation in "Question Answering Systems Project: Semantic Technologies in IBM Watson" (in parallel)
  • basic knowledge in one or several of Computational linguistics, Information Retrieval, Knowledge Representation and Machine Learning Advantageous
  • advanced knowledge in one or several of Computational linguistics, Information Retrieval, Knowledge Representation and Machine Learning

Important Dates for 2014 Edition

The seminar will be conducted in two sessions. Participation is compulsory:

  • April 24, 2014, 14:00-16:00, S2|02 A126: General Introduction, Distribution of Topics
  • May 26-27 2014, 14:00-18:00, S2/02 A313: Seminar with student presentations

May 26, 2014: S2/02 A313

    14:00 - 14:05 : Introduction by Prof. Dr. Chris Biemann

  1. Alexander Gabriel: Question analysis: How Watson reads a clue - A. Lally, J. M. Prager, M. C. McCord, B. K. Boguraev, S. Patwardhan, J. Fan, P. Fodor, and J. Chu-Carroll

    Supervisor: Prof. Dr. Chris Biemann

    Time: 14:05 - 14:40
  2. Jonas Klesy: Deep parsing in Watson - M. C. McCord, J. W. Murdock, and B. K. Boguraev

    Supervisor: Prof. Dr. Chris Biemann

    Time: 14:40 - 15:15
  3. Marc Arndt: Textual resource acquisition and engineering - J. Chu-Carroll, J. Fan, N. Schlaefer, and W. Zadrozny

    Supervisor: Prof. Dr. Chris Biemann

    Time: 15:15 - 15:50

     

    Coffee break: 15:50 - 16:10

     

  4. Jonas Mantel: Automatic knowledge extraction from documents - J. Fan, A. Kalyanpur, D. C. Gondek, and D. A. Ferrucci

    Supervisor: Prof. Dr. Chris Biemann

    Time: 16:10 - 16:45
  5. Viktoria Brost: Finding needles in the haystack: Search and candidate generation - J. Chu-Carroll, J. Fan, B. K. Boguraev, D. Carmel, D. Sheinwald, and C. Welty 

    Supervisor: Prof. Dr. Chris Biemann

    Time: 16:45 - 17:20

    Closing remarks: 17:20 - 17:25

May 27, 2014: S2/02 A313

           14:00 - 14:05 : Introduction by Prof. Dr. Chris Biemann

  1. Thorben Hehmann: Typing candidate answers using type coercion - J. W. Murdock, A. Kalyanpur, C. Welty, J. Fan, D. A. Ferrucci, D. C. Gondek, L. Zhang, and H. Kanayama

    Supervisor: Prof. Dr. Johannes Fürnkranz

    Time: 14:05 - 14:40
  2. Matthias Schultheis: Identifying implicit relationships - J. Chu-Carroll, E. W. Brown, A. Lally, and J. W. Murdock

    Supervisor: Prof. Dr. Chris Biemann

    Time: 14:40 - 15:15
  3. Michael Stahr: A framework for merging and ranking of answers in DeepQA - D. C. Gondek, A. Lally, A. Kalyanpur, J. W. Murdock, P. A. Duboue, L. Zhang, Y. Pan, Z. M. Qiu, and C. Welty

    Supervisor: Prof. Dr. Johannes Fürnkranz

    Time: 15:15 - 15:50

     

    Coffee break: 15:50 - 16:10

     

  4. Marco Balhausen: Making Watson fast - E. A. Epstein, M. I. Schor, B. S. Iyer, A. Lally, E. W. Brown, and J. Cwiklik

    Supervisor: Prof. Dr. Johannes Fürnkranz

    Time: 16:10 - 16:45
  5. Janine Hoelscher: Simulation, learning, and optimization techniques in Watson’s game strategies - G. Tesauro, D. C. Gondek, J. Lenchner

    Supervisor: Prof. Dr. Johannes Fürnkranz

    Time: 16:45 - 17:20

    Closing remarks: 17:20 - 17:25

A A A | Drucken Print | Impressum Impressum | Sitemap Sitemap | Suche Search | Kontakt Contact | Webseitenanalyse: Mehr Informationen
zum Seitenanfangzum Seitenanfang