Classifies Coherent Locution Pairs as either Arguing, Disagreeing, or N/A Illocutionary Force. N/A consists of instances where there are other and no illocutionary forces present in the sentence pair.

Takes two coherent Locutions and classifies as either Arguing, Disagreeing, or N/A.

Results:

precision recall f1-score support
Arguing 0.57 0.51 0.54 110
Disagreeing 0.35 0.36 0.36 22
N/A 0.80 0.83 0.82 289
accuracy 0.72 421
macro avg 0.57 0.57 0.57 421
weighted avg 0.72 0.72 0.72 421

Dataset: https://corpora.aifdb.org/mm123 The data preprocessing and fine-tuning technique can be found here: https://discovery.dundee.ac.uk/en/studentTheses/exploiting-illocutionary-forces-in-dialogue-structures-for-enhanc/

Downloads last month
2
Safetensors
Model size
0.4B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support