Deep Learning Architectures for Argument Mining Tasks
Deep learning architectures for solving the three major argument mining tasks: argumentative fragment detection, argument component classification, and argumentative relation recognition.
Dataset
The data used are the small version of the decide-madrid-2019 dataset annotated for argument mining tasks.
The corpus is composed of the 40 most controversial proposals, where, collaboratively, the arguments given by citizens in the descriptions and comments of the proposals were searched and annotated.
The first version of this corpus is publicly available in the following repository.
Pretrained Model
The contextualized model in Spanish that we are using is BETO: https://github.com/dccuchile/beto
- HuggingFace cased model: https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased
- HuggingFace uncased model: https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased
Documentation
Please read the contributing and code of conduct documentation.
Authors
Created on Sep 19, 2023
Created by:
License
This project is licensed under the terms of the Apache License 2.0.
Acknowledgements
This work was supported by the Spanish Ministry of Science and Innovation (PID2019-108965GB-I00).