Self-Contextualized Attention for Abusive Language Identification

Horacio Jarquín-Vásquez, Hugo Jair Escalante, Manuel Montes


Abstract
The use of attention mechanisms in deep learning approaches has become popular in natural language processing due to its outstanding performance. The use of these mechanisms allows one managing the importance of the elements of a sequence in accordance to their context, however, this importance has been observed independently between the pairs of elements of a sequence (self-attention) and between the application domain of a sequence (contextual attention), leading to the loss of relevant information and limiting the representation of the sequences. To tackle these particular issues we propose the self-contextualized attention mechanism, which trades off the previous limitations, by considering the internal and contextual relationships between the elements of a sequence. The proposed mechanism was evaluated in four standard collections for the abusive language identification task achieving encouraging results. It outperformed the current attention mechanisms and showed a competitive performance with respect to state-of-the-art approaches.
Anthology ID:
2021.socialnlp-1.9
Volume:
Proceedings of the Ninth International Workshop on Natural Language Processing for Social Media
Month:
June
Year:
2021
Address:
Online
Editors:
Lun-Wei Ku, Cheng-Te Li
Venue:
SocialNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
103–112
Language:
URL:
https://aclanthology.org/2021.socialnlp-1.9
DOI:
10.18653/v1/2021.socialnlp-1.9
Bibkey:
Cite (ACL):
Horacio Jarquín-Vásquez, Hugo Jair Escalante, and Manuel Montes. 2021. Self-Contextualized Attention for Abusive Language Identification. In Proceedings of the Ninth International Workshop on Natural Language Processing for Social Media, pages 103–112, Online. Association for Computational Linguistics.
Cite (Informal):
Self-Contextualized Attention for Abusive Language Identification (Jarquín-Vásquez et al., SocialNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.socialnlp-1.9.pdf