|
--- |
|
tags: |
|
- xlm-roberta |
|
- adapter-transformers |
|
- adapterhub:mlki/ep |
|
license: "apache-2.0" |
|
--- |
|
|
|
# Adapter `xlm-roberta-large_mlki_ep_pfeiffer` for xlm-roberta-large |
|
|
|
**Note: This adapter was not trained by the AdapterHub team, but by these author(s): Yifan Hou. |
|
See author details below.** |
|
|
|
Knowledge adapter set for multilingual knowledge graph integration. This adapter is for cross-lingual entity alignment enhancement (phrase-level). We trained it with alignments from Wikidata across 84 languages. |
|
|
|
**This adapter was created for usage with the [Adapters](https://github.com/Adapter-Hub/adapters) library.** |
|
|
|
## Usage |
|
|
|
First, install `adapters`: |
|
|
|
``` |
|
pip install -U adapters |
|
``` |
|
|
|
Now, the adapter can be loaded and activated like this: |
|
|
|
```python |
|
from adapters import AutoAdapterModel |
|
|
|
model = AutoAdapterModel.from_pretrained("xlm-roberta-large") |
|
adapter_name = model.load_adapter("AdapterHub/xlm-roberta-large_mlki_ep_pfeiffer") |
|
model.set_active_adapters(adapter_name) |
|
``` |
|
|
|
## Architecture & Training |
|
|
|
- Adapter architecture: pfeiffer |
|
- Prediction head: None |
|
- Dataset: [MLKI_EP](https://github.com/yifan-h/Multilingual_Space) |
|
|
|
## Author Information |
|
|
|
- Author name(s): Yifan Hou |
|
- Author email: yifan.hou@inf.ethz.ch |
|
- Author links: [Website](https://yifan-h.github.io/), [GitHub](https://github.com/eth-nlped), [Twitter](https://twitter.com/yyyyyyyyifan) |
|
|
|
|
|
|
|
## Citation |
|
|
|
```bibtex |
|
@article{hou2022adapters, title={Adapters for Enhanced Modeling of Multilingual Knowledge and Text}, author={Hou, Yifan and Jiao, Wenxiang and Liu, Meizhen and Allen, Carl and Tu, Zhaopeng and Sachan, Mrinmaya}, journal={arXiv preprint arXiv:2210.13617}, year={2022} } |
|
``` |
|
|
|
*This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/mlki/xlm-roberta-large_mlki_ep_pfeiffer.yaml*. |
