MITCH, which ran from 2004 until 2009, was part of NWO's CATCH programme (continuous access to cultural heritage), an intiative to develop and use information technologies to disclose the knowledge inside the vast archives of the Dutch cultural heritage. The MITCH project was a joint effort of the ILK Research Group of the Tilburg centre for Creative Computing at Tilburg University, and Naturalis, the Dutch National Museum of Natural History.

The acronym MITCH stands for mining for information in texts from the cultural heritage. Here, mining refers to text data mining or knowledge-discovery in text; the process of extracting interesting and non-trivial information and knowledge from unstructured text. The goal of the MITCH project was to research and develop techniques to discover new meaning in large collections of partially structured data that are available at Naturalis, the Dutch National Museum of Natural History.

• MITCH Publications
• ILK publications (including other publications by MITCH team members)

• Timpute
  automated database cleanup by memory-based data imputation
• mBase
  Interface for browsing and searching results of error correction and automatic segmentation research (web demo)

• Pop science article Delven in het museum (in Dutch) about the MITCH project at Kennislink. January, 2010

• Short film CATCH, the future highlighting NWO's CATCH programme, featuring the MITCH project and Marieke van Erp. November, 2009

• General MITCH overview presented on November 13, 2009 at the NWO How to CATCH the Future Symposium


• Marieke van Erp talks about text mining and the MITCH project at Noorderlicht Radio on Tuesday January 27, 2009, 15:30 (on Dutch national channel "Radio 1"). Listen to the podcast. January 26, 2009

MITCH has initiated a workshop series under the acronym LaTeCH: Language Technology for Cultural Heritage Data. The first workshop, LaTeCH-07, was held at ACL-2007 in Prague, Czech Republic, on June 28, 2007. The ACL Anthology offers the complete proceedings online (also see the bibtex file).

In 2008 we co-organised LaTeCH-08 at the 6th edition of the Language Resources and Evaluation Conference (LREC-08), on June 1, 2008, in Marrakech, Morocco. The special theme of this workshop was "Resources and Tools for Studying Language Variety and Change".

In March 2009 we organised the 'LaTeCH - SHELT&R 2009' workshop on Language Technology and Resources for Cultural Heritage, Social Sciences, Humanities, and Education.

The LaTeCH 2010 workshop will be a satellite event of ECAI-2010, held in August 2010, in Lisbon, Portugal.