• Publications
  • Influence
NADI 2020: The First Nuanced Arabic Dialect Identification Shared Task
TLDR
We present the results and findings of the First Nuanced Arabic Dialect Identification Shared Task (NADI). Expand
AraNet: A Deep Learning Toolkit for Arabic Social Media
TLDR
We describe AraNet, a collection of deep learning Arabic social media processing tools. Expand
NADI 2021: The Second Nuanced Arabic Dialect Identification Shared Task
TLDR
We present the findings and results of theSecond Nuanced Arabic Dialect IdentificationShared Task (NADI 2021). Expand
Happy Together: Learning and Understanding Appraisal From Natural Language
TLDR
We develop models based on deep neural networks for the task, including uni- and bi-directional long short-term memory networks, with and without attention. Expand
No Army, No Navy: BERT Semi-Supervised Learning of Arabic Dialects
TLDR
We develop tweet-level identification models based on GRUs and BERT in supervised and semi-supervised set-tings. Expand
Multi-Task Bidirectional Transformer Representations for Irony Detection
TLDR
We show how we mitigate this need by fine-tuning the pre-trained bidirectional encoders from transformers (BERT) on gold data. Expand
Leveraging Affective Bidirectional Transformers for Offensive Language Detection
TLDR
We develop an effective method for automatic data augmentation and show the utility of training both offensive and hate speech models off (i.e., by fine-tuning) previously trained affective models. Expand
DiaNet: BERT and Hierarchical Attention Multi-Task Learning of Fine-Grained Dialect
TLDR
We introduce a hierarchical attention multi-task learning (HA-MTL) approach for dialect identification exploiting our data at the city, state, and country levels. Expand
Sentence-Level BERT and Multi-Task Learning of Age and Gender in Social Media
TLDR
We exploit a newly-created Arabic dataset with ground truth age and gender labels to learn these attributes both individually and in a multi-task setting at the sentence level. Expand
UBC-NLP at SemEval-2019 Task 6: Ensemble Learning of Offensive Content With Enhanced Training Data
TLDR
We investigate the utility of using various data enhancement methods with a host of classical ensemble classifiers with limited, imbalanced data. Expand
...
1
2
...