NLP at SemEval-2019 Task 6: Detecting Offensive language using Neural Networks

• DOI: 10.18653/v1/s19-2105
• Publication Date: 2019-07-21T13:29:51Z
• Authors: Prashant Kapil; Asif Ekbal; Dipankar Das
• Keywords: SemEval; Offensive

In this paper we built several deep learning architectures to participate in shared task OffensEval: Identifying and categorizing Offensive language Social media by semEval-2019. The dataset was annotated with three level annotation schemes detect between offensive not offensive, categorization target identification contents. Deep models POS information as feature were also leveraged for classification. best that performed on individual sub tasks are stacking of CNN-Bi-LSTM Attention, BiLSTM added word features Bi-LSTM third task. Our achieved a Macro F1 score 0.7594, 0.5378 0.4588 Task(A,B,C) respectively rank 33rd, 54th 52nd out 103, 75 65 submissions.The using Neural Networks.