Urszula Walińska


2020

pdf bib
Urszula Walińska at SemEval-2020 Task 8: Fusion of Text and Image Features Using LSTM and VGG16 for Memotion Analysis
Urszula Walińska | Jędrzej Potoniec
Proceedings of the Fourteenth Workshop on Semantic Evaluation

In this paper, we describe the entry to the task of Memotion Analysis. The sentiment analysis of memes task, is motivated by a pervasive problem of offensive content spread in social media, up to the present time. In fact, memes are an important medium of expressing opinion and emotions, therefore they can be hateful at many times. In order to identify emotions expressed by memes we construct a tool based on neural networks and deep learning methods. It takes an advantage of a multi-modal nature of the task and performs fusion of image and text features extracted by models dedicated to this task. Moreover, we show that visual information might be more significant in the sentiment analysis of memes than textual one. Our solution achieved 0.346 macro F1-score in Task A – Sentiment Classification, which brought us to the 7th place in the official rank of the competition.

pdf bib
PUM at SemEval-2020 Task 12: Aggregation of Transformer-based Models’ Features for Offensive Language Recognition
Piotr Janiszewski | Mateusz Skiba | Urszula Walińska
Proceedings of the Fourteenth Workshop on Semantic Evaluation

In this paper, we describe the PUM team’s entry to the SemEval-2020 Task 12. Creating our solution involved leveraging two well-known pretrained models used in natural language processing: BERT and XLNet, which achieve state-of-the-art results in multiple NLP tasks. The models were fine-tuned for each subtask separately and features taken from their hidden layers were combinedand fed into a fully connected neural network. The model using aggregated Transformer featurescan serve as a powerful tool for offensive language identification problem. Our team was ranked7th out of 40 in Sub-task C - Offense target identification with 64.727% macro F1-score and 64thout of 85 in Sub-task A - Offensive language identification (89.726% F1-score).