Commit
•
f1c44a3
1
Parent(s):
0e00179
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,23 @@
|
|
1 |
---
|
2 |
license: cc-by-nc-sa-3.0
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: cc-by-nc-sa-3.0
|
3 |
+
metrics:
|
4 |
+
- f1
|
5 |
+
- accuracy
|
6 |
+
widget:
|
7 |
+
- text: "The price keeps rising."
|
8 |
---
|
9 |
+
|
10 |
+
# Multilingual-Metaphor-Detection
|
11 |
+
|
12 |
+
This page provides a fine-tuned multilingual language model [XLM-RoBERTa](https://arxiv.org/pdf/1911.02116.pdf) for metaphor detection on a token-level using [Huggingface](https://huggingface.co/tasks/token-classification).
|
13 |
+
|
14 |
+
# Dataset
|
15 |
+
The dataset the model is trained on is the [VU Amsterdam Metaphor Corpus](http://www.vismet.org/metcor/documentation/home.html) that was annotated on a word-level following the metaphor identification protocol. The training corpus is restricted to English, however, XLM-R shows decent zero-shot performances when tested on other languages.
|
16 |
+
|
17 |
+
# Results
|
18 |
+
Following the evaluation criteria from the [2020 Second Shared Task on Metaphor detection](https://competitions.codalab.org/competitions/22188#results) our model achieves a F1-Score of 0.76 for the metaphor-class when training XLM-R<sub>Base</sub> and 0.77 when training XLM-R<sub>Large.</sub>.
|
19 |
+
|
20 |
+
We train for 8 epochs loading the model with the best evaluation performance at the end and using a learning rate of 2e-5. From the allocated training data 10% are utilized for validation while the final test set is being kept seperate and only used for the final evaluation.
|
21 |
+
|
22 |
+
# Code for Training
|
23 |
+
The training and evaluation code is available on [Github](https://github.com/lwachowiak/Multilingual-Metaphor-Detection/edit/main/README.md)
|