Recognition and parsing of references to literature is a long-standing problem in the processing of historical or scholarly texts in the domains of the humanities, law and the social sciences. We invite contributions to a hybrid workshop addressing what the current state of the art in reference extraction is and how recent technological advances like large language models may help improve it.
The workshop will be held in a hybrid format on 15/16 May 2023 at the Max Planck Institute for Legal History and Legal Theory, Frankfurt/Main, Germany.
We are calling for contributions to the following and related topics/questions:
What are use cases and current projects?
What precise (sub-)tasks can we identify?
State of the art
What is the performance of current approaches?
How can the newly emerging technologies be leveraged to improve upon existing solutions?
Pooling of tools and resources
What training corpora are available? Which are needed, and in what format?
What workflows/toolchains do we need?
What infrastructure is required/available?
Should we establish a Shared Task? Write a whitepaper? Hold a hackathon?
Please also consider contributing if you have suitable training data or if you are working on related tasks like preparation of datasets, linking of references, etc.
Please send your submission to email@example.com. Deadline for submissions is Feb 28th 2023. All submitters will be notified of their status by March 13th 2023.