Centrum für Informations- und Sprachverarbeitung

Links and Functions

Breadcrumb Navigation

Home
Digital Humanities

Main Navigation

print

Content

Digital Humanities

Workshop September 14/15, 2015

More info here.

Digital Humanities

The humanities are of fundamental importance to humankind. Economic power, political decisions and the way we communicate in a global world are ultimately shaped by the subjects that the humanities study: knowledge, ideas, attitudes, values and their transmission over time and between groups of people.

The methodology of the humanities is changing rapidly because of mass digitization. It is likely that all printed material and all cultural artifacts will be easily accessible in electronic form in the future.

These developments are giving rise to the new field of digital humanities. In addition to established research methods, digital humanists take advantage of scientific advances in computer science, in particular in natural language processing, and use new computational methods for quantitative analysis, for rapid and precise identification of pertinent sources and for meaningful inspection of collections of items as opposed to sequential viewing of individual items. When accessing and analyzing the entire corpus of relevant material at once, the digital humanist can pose new types of questions that up to this point could not be answered.

Digital Humanities Research at CIS

The Center for Information and Language Processing (CIS) conducts basic research in natural language processing and information retrieval. Many results of this research are directly relevant to the digital humanities. For example, we work on advanced text preprocessing methods. This benefits the digital humanities because most automatic analysis of language in digital form requires some form of preprocessing that recognizes words and their function in context.

In addition, there are five ongoing research efforts at CIS that specifically focus on digital humanities research questions. We give one-sentence summaries below and invite you to follow the links to learn more about each project.

Digital Humanities Publications

CIS OCR Group

This is the work done at CIS in OCR of historical documents. more
Wittgenstein Advanced Search Tools (WAST)
Using the work of Ludwig Wittgenstein as an example, this project is developing rich computational linguistics and search functionalities – including local grammars, customized lexicons and symmetrical index structures – that demonstrate that electronic editions offer a powerful new research paradigm to the digital humanist. more
Edition of Wittgenstein’s writings in the Wiener Ausgabe: New Concepts to Record, Archive, Edit, Disseminate and Study Written Cultural Heritance.
This project is developing electronic apparatuses for the edition of Wittgenstein’s writings in the WIENER AUSGABE, which include rich computational linguistics and search functionalities, based on local grammars, customised lexicons and symmetrical index structures. Based on the complexity of Wittgenstein’s Nachlass the project will develop new concepts to record, archive, edit, disseminate and study written cultural heritance. more
"Alte Schulhefte" - school exercise books
The project builds a comprehensive platform for uploading, archiving, sharing, browsing, searching and discussing "alte Schulhefte" - school exercise books. "alte Schulhefte" was created in 2013 as an OJS-application (http://alteschulhefte.net/) by Alois Pichler from the Wittgenstein Archives at the University of Bergen (WAB) and is now jointly run and developed further by Alois Pichler (WAB) and Ulrike Handelshauser and Max Hadersbeck from the Centrum für Informations- und Sprachverarbeitung (CIS) at the LMU Munich. more
- Bachelorwork SS2015: U. Handelshauser
- Member of "alte Schulhefte"
Multimedial FinderApp for Goethes Faust.
The project builds the FinderApp Goethefind, which presents the search-hits not only as text, but as facsimile, video and audio output.
Management: Max Hadersbeck from the Centrum für Informations- und Sprachverarbeitung (CIS) at the LMU Munich. more
- Members of "GoetheFind"
Typology and Dialect Dynamism: Analysis of Data from Contemporary Media

In collaboration with Romance Linguistics (Prof. Krefeld), we are working on new natural language processing methods for Italian dialect data from user-generated media (e.g. Twitter and Wikipedia) to look at questions like the dynamic development of dialects over time and how they are influenced by each other and the national standard. more
Paraphrase and Coreference in Monolingual and Bilingual Parallel Corpora

Starting from the observation that most important works of literature have been translated many times into the main national languages, we are constructing monolingual parallel corpora as a new type of resource for linguistics and literary studies and use them for research on a number of different NLP problems initially focusing on coreference resolution and paraphrase generation. more

print

top

Service