Ghmerti at SemEval-2019 Task 6: A Deep Word- and Character-based Approach to Offensive Language Identification

Ehsan Doostmohammadi, Hossein Sameti, Ali Saffar


Abstract
This paper presents the models submitted by Ghmerti team for subtasks A and B of the OffensEval shared task at SemEval 2019. OffensEval addresses the problem of identifying and categorizing offensive language in social media in three subtasks; whether or not a content is offensive (subtask A), whether it is targeted (subtask B) towards an individual, a group, or other entities (subtask C). The proposed approach includes character-level Convolutional Neural Network, word-level Recurrent Neural Network, and some preprocessing. The performance achieved by the proposed model is 77.93% macro-averaged F1-score.
Anthology ID:
S19-2110
Volume:
Proceedings of the 13th International Workshop on Semantic Evaluation
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota, USA
Editors:
Jonathan May, Ekaterina Shutova, Aurelie Herbelot, Xiaodan Zhu, Marianna Apidianaki, Saif M. Mohammad
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
617–621
Language:
URL:
https://aclanthology.org/S19-2110
DOI:
10.18653/v1/S19-2110
Bibkey:
Cite (ACL):
Ehsan Doostmohammadi, Hossein Sameti, and Ali Saffar. 2019. Ghmerti at SemEval-2019 Task 6: A Deep Word- and Character-based Approach to Offensive Language Identification. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 617–621, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
Cite (Informal):
Ghmerti at SemEval-2019 Task 6: A Deep Word- and Character-based Approach to Offensive Language Identification (Doostmohammadi et al., SemEval 2019)
Copy Citation:
PDF:
https://aclanthology.org/S19-2110.pdf
Code
 edoost/offenseval
Data
OLID