This paper describes our system submissions as part of our participation (team name: JU ETCE 17 21) in the SemEval 2019 shared task 6: "OffensEval: Identifying and Categorizing Offensive Language in Social Media". We participated in all the three sub-tasks: i) Sub-task A: offensive language identification, ii) Sub-task B: automatic categorization of offense types, and iii) Sub-task C: offense target identification. We employed machine learning as well as deep learning approaches for the sub-tasks. We employed Convolutional Neural Network (CNN) and Recursive Neural Network (RNN) Long Short-Term Memory (LSTM) with pre-trained word embeddings. We used both word2vec and Glove pre-trained word embeddings. We obtained the best F1score using CNN based model for sub-task A, LSTM based model for sub-task B and Logistic Regression based model for sub-task C. Our best submissions achieved 0.7844, 0.5459 and 0.48 F1-scores for sub-task A, sub-task B and sub-task C respectively.

No abstract

No abstract

No abstract

Zero-shot Learning (ZSL) is a transfer learning technique which aims at transferring knowledge from seen classes to unseen classes. This knowledge transfer is possible because of underlying semantic space which is common to seen and unseen classes. Most existing approaches learn a projection function using labeled seen class data which maps visual data to semantic data. In this work, we propose a shallow but effective neural network-based model for learning such a projection function which aligns the visual and semantic data in the latent space while simultaneously making the latent space embeddings discriminative. As the above projection function is learned using the seen class data, the so-called projection domain shift exists. We propose a transductive approach to reduce the effect of domain shift, where we utilize unlabeled visual data from unseen classes to generate corresponding semantic features for unseen class visual samples. While these semantic features are initially generated using a conditional variational autoencoder, they are used along with the seen class data to improve the projection function. We experiment on the both inductive and transductive setting of ZSL and generalized ZSL and show superior performance on standard benchmark datasets AWA1, AWA2, CUB, SUN, FLO, and APY. We also show the efficacy of our model in the case of extremely less labeled data regime on different datasets in the context of ZSL.