Identifying attack and support argumentative relations using deep learning

Oana Cocarascu, Francesca Toni


Abstract
We propose a deep learning architecture to capture argumentative relations of attack and support from one piece of text to another, of the kind that naturally occur in a debate. The architecture uses two (unidirectional or bidirectional) Long Short-Term Memory networks and (trained or non-trained) word embeddings, and allows to considerably improve upon existing techniques that use syntactic features and supervised classifiers for the same form of (relation-based) argument mining.
Anthology ID:
D17-1144
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1374–1379
Language:
URL:
https://aclanthology.org/D17-1144
DOI:
10.18653/v1/D17-1144
Bibkey:
Cite (ACL):
Oana Cocarascu and Francesca Toni. 2017. Identifying attack and support argumentative relations using deep learning. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1374–1379, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Identifying attack and support argumentative relations using deep learning (Cocarascu & Toni, EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1144.pdf
Data
SNLI