lorenzozan
/

ME2-BERT

Text Classification

feature-extraction

Moral Foundation Prediction

Morality Values

BERTForMoralPrediction

https://aclanthology.org/2025.coling-main.638.pdf

Model card Files Files and versions

lorenzozan commited on Jan 31, 2025

Commit

e4747bb

·

verified ·

1 Parent(s): 5d2a50e

Update README.md

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -19,9 +19,7 @@ license: mit
 In this work, we propose ME²-BERT, the first holistic  framework for fine-tuning a pre-trained language model like BERT to the task of moral foundation prediction. ME²-BERT integrates events and emotions for learning domain-invariant morality-relevant text representations.
 Our extensive experiments show that ME²-BERT outperforms existing state-of-the-art methods for moral foundation prediction, with an average percentage increase up to 35% in the out-of-domain scenario.
-The source code is available [here](https://github.com/lorenzozangari/ME2-BERT). The link to the paper is [here](https://github.com/lorenzozangari/ME2-BERT).
 ## Training Data
 ME²-BERT was fine-tuned on the [**E2MoCase dataset**](https://arxiv.org/pdf/2409.09001) (available upon request), which consists of 97,251 paragraphs from news articles encompassing both event-based and event-free samples. It includes annotations for:

 In this work, we propose ME²-BERT, the first holistic  framework for fine-tuning a pre-trained language model like BERT to the task of moral foundation prediction. ME²-BERT integrates events and emotions for learning domain-invariant morality-relevant text representations.
 Our extensive experiments show that ME²-BERT outperforms existing state-of-the-art methods for moral foundation prediction, with an average percentage increase up to 35% in the out-of-domain scenario.
+The link to the paper is [here](https://github.com/lorenzozangari/ME2-BERT). The source code is available [here](https://github.com/lorenzozangari/ME2-BERT).
 ## Training Data
 ME²-BERT was fine-tuned on the [**E2MoCase dataset**](https://arxiv.org/pdf/2409.09001) (available upon request), which consists of 97,251 paragraphs from news articles encompassing both event-based and event-free samples. It includes annotations for: