FactMine

FactMine was a research project which was part of the research programme Interactive Multimodal Information Extraction (IMIX) which was sponsored by the Dutch Research Council (NWO). The goal of the project was to develop unsupervised methods for the extraction of fact bases and ontological information from text. The project ran at the Informatics Institute of the University of Amsterdam for the period November 2004 to December 2007 and employed one postdoc, Erik Tjong Kim Sang.

Initial documents

• Research proposal (pdf).
• Project description (html).

Software demos

• Question answering demo
• Question classification demo
• Concept tagging demo
• Named entity tagging demo

Publications and talks

• Erik Tjong Kim Sang and Katja Hofmann, Automatic Extraction of Dutch Hypernym-Hyponym Pairs. Published in the Proceedings of CLIN-2006, Leuven, Belgium, 2007. [pdf]
• Katja Hofmann and Erik Tjong Kim Sang, Automatic Extension of Non-English WordNets. Poster presented at SIGIR'07, Amsterdam, The Netherlands, 2007. [pdf]
• Erik Tjong Kim Sang, Extracting Hypernym Pairs from the Web. Poster presented at ACL 2007, Prague, Czech Republic, 2007. [pdf]
• Erik Tjong Kim Sang, Deriving Knowledge from Dutch Medical Text, poster presented at SIREN-2005, in Eindhoven, The Netherlands, 6 October 2005. [pdf]
• Erik Tjong Kim Sang, Gosse Bouma and Maarten de Rijke, Developing Offline Strategies for Answering Medical Questions. Short paper published in the Proceedings of the AAAI-05 Workshop on Question Answering in Restricted Domains, Pittsburgh, PA, USA, 2005, pp. 41-45. [pdf] [data]
• Erik Tjong Kim Sang, Introduction to FactMine, poster presented at CLIN-2004, in Leiden, The Netherlands, 17 December 2004. [pdf]
• Erik Tjong Kim Sang, IMIX in Amsterdam: FactMine, talk presented at the IMIX Presentation Day in Utrecht, The Netherlands, 2 December 2004. [pdf]

Background literature

• Michael Fleischman, Eduard Hovy, and Abdessamad Echihabi, Offline Strategies for Online Question Answering: Answering Questions Before They Are Asked. In: Proceedings of ACL-2003, Sapporo, Japan. 2003.
  http://www.mit.edu/~mbf/ACL_03.pdf
• Valentin Jijkoun, Gilad Mishne, and Maarten de Rijke. Preprocessing Documents to Answer Dutch Questions. In: Proceedings of BNAIC'03, Nijmegen, The Netherlands, 2003.
  http://staff.science.uva.nl/~gilad/pubs/bnaic03.pdf
• Jori Mur, Offline answer extraction using Dependency Relations. Masters thesis, Humanities Computing, Groningen, The Netherlands, 2004.
  http://odur.let.rug.nl/mur/papers/scriptie.pdf
• Patrick Pantel and Deepak Ravichandran, Automatically Labeling Semantic Classes. In: Proceedings of HLT-NAACL 2004, pp. 321-328. Boston, MA, USA, 2004. http://morrison.isi.edu/cgi-bin/Web/Tools/getfile.pl?type=paper&id=2004/naacl04.pdf
• Brian Roark and Eugene Charniak, Noun-phrase co-occurrence statistics for semi-automatic semantic lexicon construction. In: Proceedings of ACL-98, Montreal, Quebec, Canada, 1998.
  http://arxiv.org/abs/cs.CL/0008026
• Leonie IJzereef, Automatische extractie van hyponiemrelaties uit grote tekstcorpora. Masters thesis, Humanities Computing, Groningen, The Netherlands, 2004.
  http://www.let.rug.nl/alfa/scripties/LeonieIJzereef.pdf