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
- 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)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/S19-2110.pdf
- Code
- edoost/offenseval
- Data
- OLID