|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
- fr |
|
|
- de |
|
|
- la |
|
|
- it |
|
|
base_model: |
|
|
- sven-nm/XLM-R-for-classics |
|
|
pipeline_tag: token-classification |
|
|
--- |
|
|
|
|
|
This model is fine-tuned for historical bibliographical named-entity recognition [AjMC-NE-Corpus](https://github.com/AjaxMultiCommentary/AjMC-NE-corpus), so as release in [HIPE-2](https://doi.org/10.1007/978-3-031-13643-6_26), for 40 epochs, beating all our other models. |
|
|
It is intended to detect persons (authors, mythological...), works (primary and secondary literature, fragments), objects (manuscript, inscriptions), locations, dates, and scopes (i.e. reference scopes, such as Hom. Il. _XI, 106-122_). |
|
|
It can be used in a normal token classification pipeline. |
|
|
|
