|
--- |
|
license: mit |
|
pipeline_tag: fill-mask |
|
tags: |
|
- low-resource |
|
- sigtyp |
|
- ancient-languages |
|
- historical-languages |
|
- shared-task |
|
--- |
|
|
|
# LiBERTus-base |
|
|
|
Submission to Task 1 (Constrained) of the [SIGTYP 2024 Shared Task on Word |
|
Embedding Evaluation for Ancient and Historical |
|
Languages](https://sigtyp.github.io/st2024.html). The system is built by |
|
first pretraining a multilingual language model and then finetuning it for a |
|
downstream task. The submission for Phase 1 and 2 of the Shared Task can be |
|
found in the `submission_p1` and `submission_p2` directories. |
|
|
|
If you're using this model, please cite: |
|
|
|
``` |
|
@inproceedings{miranda-2024-allen, |
|
title = "{A}llen Institute for {AI} @ {SIGTYP} 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages", |
|
author = "Miranda, Lester James", |
|
booktitle = "Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP", |
|
month = mar, |
|
year = "2024", |
|
address = "St. Julian's, Malta", |
|
publisher = "Association for Computational Linguistics", |
|
url = "https://aclanthology.org/2024.sigtyp-1.18", |
|
pages = "151--159", |
|
} |
|
``` |
