DARIAH TDA-WG and DHuF will collocate a one-day workshop with the 2018 DHd conference in Cologne on Tuesday, 27 February 2018. The workshop aims to bring together ca. 20 practitioners from the Digital Humanities to present and discuss recent advances in the field, through 30-minute presentations on focused case studies, including work-in-progress or theoretical contributions. The presentations will be started with a keynote lecture by David Bamman (University of California, Berkeley).
Additionally, the workshop aims to reach an audience of non-presenting participants who take an active interest in distributional models and who are planning to apply distributional models to their own data in the near future. We aim to bring together a diverse group of both junior and senior stakeholders in this nascent subfield of DH. The goal of the workshop is to identify the state of the art in the field, identify common challenges and share recommendations for a best practice. Special attention will be given to the (both hermeneutic and quantitative) evaluation of distributional models in the context of Humanities research, which remains a challenging issue.
The workshop is open to scholars from all backgrounds with an interest in semantic representation learning and encourages submissions that deal with under-researched, resource-scarce and/or historic languages.
We are looking for proposals that (1) give new insights in how distributional models can contribute to the humanities research. That includes more specific case studies, even if they are work in progress. We are also looking for (2) research that addresses current methodological issues like e.g.
- how to deal with polysemy in distributional models;
- the diachronic study of cultural phenomena via distributed methods;
- the evaluation of distributional models, both from an empiric and hermeneutic perspective;
- modeling the role and behaviour of (individual) readers or reading communities;
- modeling units beyond words;
- improving the theoretical understanding of word embeddings;
Abstracts (between 250 and 300 words, not including references) can be submitted until 31. January to email@example.com. The workshop also explicitly welcomes submissions presenting previously published research which is of interest to the DH community (although this work should not overlap strongly with work presented at the main conference).
The workshop is organized by the DARIAH-EU working group on “Text and Data Analytics” (@dariahtdawg)and DARIAH-DE Cluster “Quantitative Data Analysis”, sponsored by the German Federal Ministry of Education and Research (BMBF), in collaboration with the scientific community Digital Humanities Flanders (DHuF), sponsored by the Research Foundation Flanders (FWO).
For more details please visit the website of the DARIAH-EU Working Group “Text and Data Analytics”