---
language: 
  - en
tags:
- sequence tagging
- vossian antonomasia
license: "apache-2.0"
datasets:
- custom 
widget:
- text: Bijan wants Jordan to be the Elizabeth Taylor of men's fragrances.
metrics:
- f1
- precision
- recall
---

## English Vossian Antonomasia Sequence Tagger

This page presents a fine-tuned [BERT-base-cased](https://huggingface.co/bert-base-cased) language model for tagging Vossian Antonomasia expressions in text on word-level. 
The tags {B,I}-SRC refers to the source chunks, {B,I}-MOD to the modifier chunks and {B,I}-TRG to the target chunks if existing. We used the IOB tagging format.


### Dataset

The dataset is an annotated Vossian Antonomasia dataset that evolved from [Schwab et al. 2019](https://www.aclweb.org/anthology/D19-1647.pdf) and was updated in [Schwab et al. 2022](https://doi.org/10.3389/frai.2022.868249).

### Results

F1 score: 0.926


For more results, please have a look at [our paper](https://doi.org/10.3389/frai.2022.868249).

Please note, that this model was trained on the annotated dataset only and did not use any additional unlabeled training data. 
Thus, it may not be as robust as the best model in [our paper](https://doi.org/10.3389/frai.2022.868249) against new data.



---

### Cite

Please cite the following paper when using this model.

```
@article{schwab2022rodney,
  title={“The Rodney Dangerfield of Stylistic Devices”: End-to-End Detection and Extraction of Vossian Antonomasia Using Neural Networks},
  author={Schwab, Michel and J{\"a}schke, Robert and Fischer, Frank},
  journal={Frontiers in Artificial Intelligence},
  volume={5},
  year={2022},
  publisher={Frontiers Media SA}
}
```


---

### Interested in more?
Visit our [Website](http://vossanto.weltliteratur.net/) for more research on Vossian Antonomasia, including interactive visualizations for exploration.