Adapter xlm-roberta-large_mlki_tp_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 factual triple enhancement (phrase-level). We trained it with triples from Wikidata across 84 languages.

This adapter was created for usage with the Adapters library.

Usage

First, install adapters:

pip install -U adapters

Now, the adapter can be loaded and activated like this:

from adapters import AutoAdapterModel

model = AutoAdapterModel.from_pretrained("xlm-roberta-large")
adapter_name = model.load_adapter("AdapterHub/xlm-roberta-large_mlki_tp_pfeiffer")
model.set_active_adapters(adapter_name)

Architecture & Training

• Adapter architecture: pfeiffer
• Prediction head: None
• Dataset: MLKI_TP

Author Information

• Author name(s): Yifan Hou
• Author email: yifan.hou@inf.ethz.ch
• Author links: Website, GitHub, Twitter

Citation

@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_tp_pfeiffer.yaml.