Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-2.0
|
3 |
+
datasets:
|
4 |
+
- CreativeLang/vua20_metaphor
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
---
|
8 |
+
|
9 |
+
# Metaphor_Detection_Roberta_Seq
|
10 |
+
|
11 |
+
## Description
|
12 |
+
|
13 |
+
- **Paper:** [FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning](https://aclanthology.org/2023.eacl-main.114.pdf)
|
14 |
+
|
15 |
+
## Model Summary
|
16 |
+
|
17 |
+
Creative Language Toolkit (CLTK) Metadata
|
18 |
+
- CL Type: Metaphor
|
19 |
+
- Task Type: detection
|
20 |
+
- Size: roberta-base (500MB)
|
21 |
+
- Created time: 2022
|
22 |
+
|
23 |
+
This model is a easy to use metaphor detection baseline realised with `roberta-base` fine-tuned on [CreativeLang/vua20_metaphor](https://huggingface.co/datasets/CreativeLang/vua20_metaphor) dataset.
|
24 |
+
|
25 |
+
To use this model, please use the `inference.py` in the [FrameBERT repo](https://github.com/liyucheng09/MetaphorFrame).
|
26 |
+
|
27 |
+
Just run:
|
28 |
+
```
|
29 |
+
python inference.py CreativeLang/metaphor_detection_roberta_seq
|
30 |
+
```
|
31 |
+
|
32 |
+
Check out `inference.py` to learn how to apply the model on your own data.
|
33 |
+
|
34 |
+
For the details of this model and the dataset used, we refer you to the release [paper](https://aclanthology.org/2023.eacl-main.114.pdf).
|
35 |
+
|
36 |
+
### Citation Information
|
37 |
+
|
38 |
+
If you find this dataset helpful, please cite:
|
39 |
+
|
40 |
+
```
|
41 |
+
@article{Li2023FrameBERTCM,
|
42 |
+
title={FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning},
|
43 |
+
author={Yucheng Li and Shunyu Wang and Chenghua Lin and Frank Guerin and Lo{\"i}c Barrault},
|
44 |
+
journal={ArXiv},
|
45 |
+
year={2023},
|
46 |
+
volume={abs/2302.04834}
|
47 |
+
}
|
48 |
+
```
|
49 |
+
|
50 |
+
### Contributions
|
51 |
+
|
52 |
+
If you have any queries, please open an issue or direct your queries to [mail](mailto:yucheng.li@surrey.ac.uk).
|