You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

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	0.75	0.63	0.69	647
Disagreeing	0.51	0.52	0.52	143
N/A	0.67	0.77	0.72	701

accuracy			0.69	1491
macro avg	0.65	0.64	0.64	1491
weighted avg	0.69	0.69	0.69	1491

Dataset: https://corpora.aifdb.org/US2016 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/

Citation:

Inyama, G. (2025). Exploiting Illocutionary Forces in Dialogue Structures for Enhancing Authorship Identification [Master of Philosophy thesis, University of Dundee]. Discovery - the University of Dundee Research Portal. https://doi.org/10.15132/20000713

Downloads last month: -

Safetensors

Model size

0.4B params

Tensor type

F32