Wikidition: Automatic lexiconization and linkification of text corpora
-
Alexander Mehler
Alexander Mehler is professor for Computational Humanities at Goethe University and head of the Text Technology Lab. He is member of the executive committee of the
Center for the Digital Foundation of Research in the Humanities, Social, and Educational Sciences (CEDIFOR). His research interests include computational models of linguistic networks.Goethe-Universität Frankfurt, Robert-Mayer-Straße 10, D-60325 Frankfurt am Main
,
Rüdiger Gleim
Rüdiger Gleim is scientific assistant at Goethe University. He worked within the Special Research Center
Alignment in Communication at Bielefeld University. His research interests include semantic databases and text mining.Goethe-Universität Frankfurt, Robert-Mayer-Straße 10, D-60325 Frankfurt am Main
Dr. Tim vor der Brück studied Computer Science at Saarland University. Currently, he is research associate at the Lucerne University of Applied Sciences and Arts. His research interests include text mining and multimodal computing.
Hochschule Luzern, Technikumstr. 21, 6048 Horw
Wahed Hemati is project member of the CEDIFOR at Goethe University and works on machine reading and text mining.
Goethe-Universität Frankfurt, Robert-Mayer-Straße 10, D-60325 Frankfurt am Main
Tolga Uslu is project member of the CEDIFOR at Goethe University and works on image-giving methods of text mining.
Goethe-Universität Frankfurt, Robert-Mayer-Straße 10, D-60325 Frankfurt am Main
Dr. Steffen Eger is project member of the CompHistSem project at Goethe University. His research interests concern mathematical methods of computational linguistics and social network analysis.
Goethe-Universität Frankfurt, Robert-Mayer-Straße 10, D-60325 Frankfurt am Main
Abstract
We introduce a new text technology, called Wikidition, which automatically generates large scale editions of corpora of natural language texts. Wikidition combines a wide range of text mining tools for automatically linking lexical, sentential and textual units. This includes the extraction of corpus-specific lexica down to the level of syntactic words and their grammatical categories. To this end, we introduce a novel measure of text reuse and exemplify Wikidition by means of the capitularies, that is, a corpus of Medieval Latin texts.
About the authors
Alexander Mehler is professor for Computational Humanities at Goethe University and head of the Text Technology Lab. He is member of the executive committee of the Center for the Digital Foundation of Research in the Humanities, Social, and Educational Sciences (CEDIFOR). His research interests include computational models of linguistic networks.
Goethe-Universität Frankfurt, Robert-Mayer-Straße 10, D-60325 Frankfurt am Main
Rüdiger Gleim is scientific assistant at Goethe University. He worked within the Special Research Center Alignment in Communication at Bielefeld University. His research interests include semantic databases and text mining.
Goethe-Universität Frankfurt, Robert-Mayer-Straße 10, D-60325 Frankfurt am Main
Dr. Tim vor der Brück studied Computer Science at Saarland University. Currently, he is research associate at the Lucerne University of Applied Sciences and Arts. His research interests include text mining and multimodal computing.
Hochschule Luzern, Technikumstr. 21, 6048 Horw
Wahed Hemati is project member of the CEDIFOR at Goethe University and works on machine reading and text mining.
Goethe-Universität Frankfurt, Robert-Mayer-Straße 10, D-60325 Frankfurt am Main
Tolga Uslu is project member of the CEDIFOR at Goethe University and works on image-giving methods of text mining.
Goethe-Universität Frankfurt, Robert-Mayer-Straße 10, D-60325 Frankfurt am Main
Dr. Steffen Eger is project member of the CompHistSem project at Goethe University. His research interests concern mathematical methods of computational linguistics and social network analysis.
Goethe-Universität Frankfurt, Robert-Mayer-Straße 10, D-60325 Frankfurt am Main
Acknowledgement
This work has been funded by the German Federal Ministry of Education via the projects CompHistSem (www.comphistsem.org) and CEDIFOR (www.cedifor.de).
©2016 Walter de Gruyter Berlin/Boston
Articles in the same Issue
- Frontmatter
- Editorial
- Computer science in humanities
- Thematic Issue: Computer Science in Humanities
- Using standoff properties for marking-up historical documents in the humanities
- Wikidition: Automatic lexiconization and linkification of text corpora
- Design considerations for a large-scale image-based text search engine in historical manuscript collections
- Made in the humanities: Dual integral invariants for efficient edge detection
- Time modelling in digital humanities. Challenges posed by the development of a database of medieval charters
- The role of computers to understand the past. The case of archaeological research
- Self-Portrayals of GI Junior Fellows
- Decentralized communication against surveillance and privacy violation
Articles in the same Issue
- Frontmatter
- Editorial
- Computer science in humanities
- Thematic Issue: Computer Science in Humanities
- Using standoff properties for marking-up historical documents in the humanities
- Wikidition: Automatic lexiconization and linkification of text corpora
- Design considerations for a large-scale image-based text search engine in historical manuscript collections
- Made in the humanities: Dual integral invariants for efficient edge detection
- Time modelling in digital humanities. Challenges posed by the development of a database of medieval charters
- The role of computers to understand the past. The case of archaeological research
- Self-Portrayals of GI Junior Fellows
- Decentralized communication against surveillance and privacy violation
