Ruprecht-Karls-Universität Heidelberg
Institut für Computerlinguistik

Bilder vom Neuenheimer Feld, Heidelberg und der Universität Heidelberg

Information Extraction

Kursbeschreibung

Studiengang Modulkürzel Leistungs-
bewertung
BA-2010[100%|75%] CS-CL 6 LP
BA-2010[50%|25%] BS-CL, BS-AC 4 LP
NBA[100%|75%] CS-CL 6 LP
NBA[50%|25%] BS-CL, BS-AC 4 LP
Magister - -
Dozenten/-innen Vivi Nastase
Veranstaltungsart Proseminar
Erster Termin 23.04.2012
Zeit und Ort Mo, 14:1515:45, INF 325 / SR 23 (SR)

Leistungsnachweis

  • implement a seminar project
  • pass a written exam

Inhalt

In this course we will study methods to deal with large amounts of textual data, and how to extract relevant information for various tasks.

The first part of the semester will consist of lectures, the second part will consist of student presentations based on papers on the topic that I will assign to them. Throughout the semester students will have to implement an IR system, and give a demo and short presentation at the end of the course.

Kursübersicht

Seminarplan

Datum Sitzung Materialien
23.04.2012 Introduction
30.04.2012 Temporal expression analysis
7.05.2012 Named entities
14.05.2012 Relation extraction
21.05.2012 Large scale IE -- Reading the Web
28.05.2012 Holiday
4.06.2012 Student presentations 1. (Marcus Husar) Concept Discovery from Text Lin & Pantel, 2002
11.06.2012 Student presentations 2. (Julian Hitschler) Corpus-based semantic class mining: distributional vs. pattern-based approaches Shi, Zhang, Yuan & Wen, 2010 (slides)
4. (Olena Shevchuk) Discovering relations between noun categories Mohamed, Hruschka & Mitchell, 2011
18.06.2012 Student presentations 5. (Carolin Guenzel) Hypernym Discovery Based on Distributional Similarity and Hierarchical Structures Yamada, Torisawa, Kazama & Kuroda, 2009
6. Unsupervised methods for developing taxonomies by combining syntactic and statistical information Widdows, 2003
25.06.2012 Student presentations 8. (Eleftherios Matios) The Tradeoffs Between Open and Traditional Relation Extraction Banko & Etzioni, 2008 (slides)
2.07.2012 Student presentations 7. (Oliver Petra) Learning to extract relations from the web using minimal supervision Bunescu & Mooney, 2007
3. Training and Evaluating a German Named Entity Recognizer with Semantic Generalization Faruqui & Pado, 2010
9.07.2012 No lecture (Vivi is away)
16.07.2012 Student project presentations
23.07.2012 Student project presentations

» weitere Kursmaterialien

zum Seitenanfang