• InformationExtractionWS1314

Welcome to the Wiki of the seminar ''Information Extraction'' in the winter semester 2013 / 2014

This seminar will be given by Elmar Haußmann and Sabine Storandt, from the chair of Prof. Dr. Hannah Bast (who will also attend the sessions). The seminar will take place every Wednesday, 4:00 pm - 6:00 pm ct., in the seminar room 00-007 in building 106. There will be no session on Wednesday, December 25, 2013, on Wednesday, January 1, 2014 (christmas break) and on Wednesday, November 6, 2013. Therefore, depending on the number of talks/participants, we will have at most 14 sessions.

Information Extraction is the task of extracting (structured) information from natural language text. We will cover interesting topics in this area with a focus on current state-of-the-art systems for Open Information Extraction. We will also cover the NLP background required for understanding.

Topics

The topics and dates will be assigned in the first sessions. Here is a tentative list of topics and systems (each of which will be roughly explained in the first session):

• NLP Basics 1/2 (POS tagging, chunking, NER, NED), Sven Lieber
• NLP Basics 2/2 (constituent / dependency parsing, SRL), Sven Lieber

• TextRunner + KnowItAll

• Distant supervision for RE without labeled data

• OpenIE using Wikipedia

• Never Ending Language Learning (Demo / Data available)

• SRL-IE

• ReVerb + R2A2 (Code available), Patrick Notz

• OLLIE (Code available), Max Lotstein

• PATTY (Demo available)

• Dependency based OpenIE (Code available)

• ClausIE (Code available)

• Relation Extraction With Matrix Factorization (Code available), Licon Jose

• Integrating Syntactic and Semantic Analysis into OpenIE

• TREC Question Answering Track

• Lymba (QA System)

Sessions

1. Wednesday October 23, 2013: Introduction and Topic Assignment Slides (Introduction + Organization, Topics)

2. Wednesday October 30, 2013: Machine Learning Introduction

3. Wednesday November 6, 2013: NO SESSION

4. Wednesday November 13, 2013: NLP Basics

5. Wednesday November 20, 2013: TextRunner + KnowItAll

6. Wednesday November 27, 2013: tbd

7. Wednesday December 4, 2013: tbd

8. Wednesday December 11, 2013: tbd

9. Wednesday December 18, 2013: tbd

10. Wednesday January 8, 2013: tbd

11. Wednesday January 15, 2013: tbd

12. Wednesday January 22, 2013: tbd

13. Wednesday January 29, 2013: tbd

14. Wednesday February 5, 2013: tbd

15. Wednesday February 12, 2013: tbd