Mohamed Elaraby


2019

pdf bib
A Character Level Convolutional BiLSTM for Arabic Dialect Identification
Mohamed Elaraby | Ahmed Zahran
Proceedings of the Fourth Arabic Natural Language Processing Workshop

In this paper, we describe CU-RAISA teamcontribution to the 2019Madar shared task2, which focused on Twitter User fine-grained dialect identification.Among par-ticipating teams, our system ranked the4th(with 61.54%) F1-Macro measure.Our sys-tem is trained using a character level convo-lutional bidirectional long-short-term memorynetwork trained on 2k users’ data. We showthat training on concatenated user tweets asinput is further superior to training on usertweets separately and assign user’s label on themode of user’s tweets’ predictions.

2018

pdf bib
You Tweet What You Speak: A City-Level Dataset of Arabic Dialects
Muhammad Abdul-Mageed | Hassan Alhuzali | Mohamed Elaraby
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Deep Models for Arabic Dialect Identification on Benchmarked Data
Mohamed Elaraby | Muhammad Abdul-Mageed
Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)

The Arabic Online Commentary (AOC) (Zaidan and Callison-Burch, 2011) is a large-scale repos-itory of Arabic dialects with manual labels for4varieties of the language. Existing dialect iden-tification models exploiting the dataset pre-date the recent boost deep learning brought to NLPand hence the data are not benchmarked for use with deep learning, nor is it clear how much neural networks can help tease the categories in the data apart. We treat these two limitations:We (1) benchmark the data, and (2) empirically test6different deep learning methods on thetask, comparing peformance to several classical machine learning models under different condi-tions (i.e., both binary and multi-way classification). Our experimental results show that variantsof (attention-based) bidirectional recurrent neural networks achieve best accuracy (acc) on thetask, significantly outperforming all competitive baselines. On blind test data, our models reach87.65%acc on the binary task (MSA vs. dialects),87.4%acc on the 3-way dialect task (Egyptianvs. Gulf vs. Levantine), and82.45%acc on the 4-way variants task (MSA vs. Egyptian vs. Gulfvs. Levantine). We release our benchmark for future work on the dataset

pdf bib
UBC-NLP at IEST 2018: Learning Implicit Emotion With an Ensemble of Language Models
Hassan Alhuzali | Mohamed Elaraby | Muhammad Abdul-Mageed
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

We describe UBC-NLP contribution to IEST-2018, focused at learning implicit emotion in Twitter data. Among the 30 participating teams, our system ranked the 4th (with 69.3% F-score). Post competition, we were able to score slightly higher than the 3rd ranking system (reaching 70.7%). Our system is trained on top of a pre-trained language model (LM), fine-tuned on the data provided by the task organizers. Our best results are acquired by an average of an ensemble of language models. We also offer an analysis of system performance and the impact of training data size on the task. For example, we show that training our best model for only one epoch with < 40% of the data enables better performance than the baseline reported by Klinger et al. (2018) for the task.

2017

pdf bib
An Unsupervised Speaker Clustering Technique based on SOM and I-vectors for Speech Recognition Systems
Hany Ahmed | Mohamed Elaraby | Abdullah M. Mousa | Mostafa Elhosiny | Sherif Abdou | Mohsen Rashwan
Proceedings of the Third Arabic Natural Language Processing Workshop

In this paper, we introduce an enhancement for speech recognition systems using an unsupervised speaker clustering technique. The proposed technique is mainly based on I-vectors and Self-Organizing Map Neural Network(SOM).The input to the proposed algorithm is a set of speech utterances. For each utterance, we extract 100-dimensional I-vector and then SOM is used to group the utterances to different speakers. In our experiments, we compared our technique with Normalized Cross Likelihood ratio Clustering (NCLR). Results show that the proposed technique reduces the speaker error rate in comparison with NCLR. Finally, we have experimented the effect of speaker clustering on Speaker Adaptive Training (SAT) in a speech recognition system implemented to test the performance of the proposed technique. It was noted that the proposed technique reduced the WER over clustering speakers with NCLR.