925
Comment:
|
3870
|
Deletions are marked like this. | Additions are marked like this. |
Line 1: | Line 1: |
#acl ElmarHaussmann:read,write All:read | #acl ElmarHaussmann:read,write Sabine Storandt:read,write All:read |
Line 3: | Line 3: |
= Welcome to the Wiki of the seminar '''Information Extraction''' in the winter semester 2013 / 2014 = | = Welcome to the Wiki of the seminar ''Information Extraction'' in the winter semester 2013 / 2014 = This seminar will be given by [[http://ad.informatik.uni-freiburg.de/staff/haussmann|Elmar Haußmann]] and [[https://ad.informatik.uni-freiburg.de/staff/storandt|Sabine Storandt]], from the chair of [[http://ad.informatik.uni-freiburg.de/staff/bast|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. |
Line 5: | Line 6: |
This seminar will be given by [[http://ad.informatik.uni-freiburg.de/staff/haussmann|Elmar Haußmann]], assisted by [[https://ad.informatik.uni-freiburg.de/staff/storandt|Sabine Storandt]]. | 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. |
Line 7: | Line 8: |
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. We will also cover the NLP background required for understanding. Here is a tentative list of topics (each of which will roughly explained in the first session): POS tagging, text chunking, entity recognition, semantic role labeling, syntax parsing, Textrunner, KnowItAll, SRL-IE, Kraken, NELL, Reverb, OLLIE, ClausIE. The topics and dates will be assigned in the first sessions. |
== 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) * [[https://www.aaai.org/Papers/IJCAI/2007/IJCAI07-429.pdf|TextRunner]] + [[http://www.sciencedirect.com/science/article/pii/S0004370205000366|KnowItAll]] * [[http://www.aclweb.org/anthology-new/P/P09/P09-1113.pdf|Distant supervision for RE without labeled data]] * [[http://ai.cs.washington.edu/www/media/papers/Wu-acl10.pdf|OpenIE using Wikipedia]] * [[http://rtw.ml.cmu.edu/rtw/|Never Ending Language Learning]] (Demo / Data available) * [[http://aclweb.org/anthology//W/W10/W10-0907.pdf|SRL-IE]] * [[http://ai.cs.washington.edu/www/media/papers/reverb.pdf|ReVerb]] + [[http://turing.cs.washington.edu/papers/etzioni-ijcai2011.pdf|R2A2]] (Code available), Patrick Notz * [[http://turing.cs.washington.edu/papers/emnlp12-mausam.pdf|OLLIE]] (Code available), Max Lotstein * [[http://www.aclweb.org/anthology-new/D/D12/D12-1104.pdf|PATTY]] (Demo available) * [[http://aclweb.org/anthology/W/W12/W12-0702.pdf|Dependency based OpenIE]] (Code available) * [[http://www.mpi-inf.mpg.de/~rgemulla/publications/delcorro13clausie.pdf|ClausIE]] (Code available) * [[http://www.cs.umass.edu/~lmyao/papers/univ-schema-tacl.pdf|Relation Extraction With Matrix Factorization]] (Code available), Licon Jose * [[http://wwwusers.di.uniroma1.it/~moro/MoroNavigli_IJCAI13.pdf|Integrating Syntactic and Semantic Analysis into OpenIE]] * [[http://trec.nist.gov/data/qamain.html|TREC Question Answering Track]] * [[http://trec.nist.gov/pubs/trec16/papers/lymba.qa.final.pdf|Lymba (QA System)]] == Sessions == 1. Wednesday October 23, 2013: '''Introduction and Topic Assignment''' [[http://ad-teaching.informatik.uni-freiburg.de/information-extraction-ws1314/session-1.pdf|Slides (Introduction + Organization, Topics)]] 1. Wednesday October 30, 2013: '''Machine Learning Introduction''' 1. Wednesday November 6, 2013: '''NO SESSION''' 1. Wednesday November 13, 2013: '''NLP Basics''' 1. Wednesday November 20, 2013: '''!TextRunner + !KnowItAll''' 1. Wednesday November 27, 2013: '''tbd''' 1. Wednesday December 4, 2013: '''tbd''' 1. Wednesday December 11, 2013: '''tbd''' 1. Wednesday December 18, 2013: '''tbd''' 1. Wednesday January 8, 2013: '''tbd''' 1. Wednesday January 15, 2013: '''tbd''' 1. Wednesday January 22, 2013: '''tbd''' 1. Wednesday January 29, 2013: '''tbd''' 1. Wednesday February 5, 2013: '''tbd''' 1. Wednesday February 12, 2013: '''tbd''' |
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)
Never Ending Language Learning (Demo / Data available)
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
Sessions
Wednesday October 23, 2013: Introduction and Topic Assignment Slides (Introduction + Organization, Topics)
Wednesday October 30, 2013: Machine Learning Introduction
Wednesday November 6, 2013: NO SESSION
Wednesday November 13, 2013: NLP Basics
Wednesday November 20, 2013: TextRunner + KnowItAll
Wednesday November 27, 2013: tbd
Wednesday December 4, 2013: tbd
Wednesday December 11, 2013: tbd
Wednesday December 18, 2013: tbd
Wednesday January 8, 2013: tbd
Wednesday January 15, 2013: tbd
Wednesday January 22, 2013: tbd
Wednesday January 29, 2013: tbd
Wednesday February 5, 2013: tbd
Wednesday February 12, 2013: tbd