no code implementations • 29 Nov 2022 • Sara Salamat, Nima Tavassoli, Behnam Sabeti, reza fahmi
The proposed model is capable of processing heterogeneous graphs to produce unified node embeddings which are then utilized for node classification or link prediction as the downstream task.
no code implementations • LREC 2020 • Seyed Arad Ashrafi Asli, Behnam Sabeti, Zahra Majdabadi, Preni Golazizian, reza fahmi, Omid Momenzadeh
Active Learning models can achieve the baseline performance (the accuracy of the model trained on the whole dataset), with a considerably lower amount of labeled data.
no code implementations • LREC 2020 • Preni Golazizian, Behnam Sabeti, Seyed Arad Ashrafi Asli, Zahra Majdabadi, Omid Momenzadeh, reza fahmi
In the current research, which is the first attempt at irony detection in Persian language, emoji prediction is used to build a pretrained model.
no code implementations • LREC 2020 • Zahra Majdabadi, Behnam Sabeti, Preni Golazizian, Seyed Arad Ashrafi Asli, Omid Momenzadeh, reza fahmi
In order to overcome this issue and extract trends using all tweets, we propose a graph-based approach where graph nodes represent tweets as well as words and hashtags.