Said Ouatik El Alaoui

Also published as: Said Ouatik El Alaoui


2020

pdf
LISAC FSDM-USMBA Team at SemEval-2020 Task 12: Overcoming AraBERT’s pretrain-finetune discrepancy for Arabic offensive language identification
Hamza Alami | Said Ouatik El Alaoui | Abdessamad Benlahbib | Noureddine En-nahnahi
Proceedings of the Fourteenth Workshop on Semantic Evaluation

AraBERT is an Arabic version of the state-of-the-art Bidirectional Encoder Representations from Transformers (BERT) model. The latter has achieved good performance in a variety of Natural Language Processing (NLP) tasks. In this paper, we propose an effective AraBERT embeddings-based method for dealing with offensive Arabic language in Twitter. First, we pre-process tweets by handling emojis and including their Arabic meanings. To overcome the pretrain-finetune discrepancy, we substitute each detected emojis by the special token [MASK] into both fine tuning and inference phases. Then, we represent tweets tokens by applying AraBERT model. Finally, we feed the tweet representation into a sigmoid function to decide whether a tweet is offensive or not. The proposed method achieved the best results on OffensEval 2020: Arabic task and reached a macro F1 score equal to 90.17%.

2018

pdf
Résumé automatique guidé de textes: État de l’art et perspectives (Guided Summarization : State-of-the-art and perspectives )
Salima Lamsiyah | Said Ouatik El Alaoui | Bernard Espinasse
Actes de la Conférence TALN. Volume 2 - Démonstrations, articles des Rencontres Jeunes Chercheurs, ateliers DeFT

Les systèmes de résumé automatique de textes (SRAT) consistent à produire une représentation condensée et pertinente à partir d’un ou de plusieurs documents textuels. La majorité des SRAT sont basés sur des approches extractives. La tendance actuelle consiste à s’orienter vers les approches abstractives. Dans ce contexte, le résumé guidé défini par la campagne d’évaluation internationale TAC (Text Analysis Conference) en 2010, vise à encourager la recherche sur ce type d’approche, en se basant sur des techniques d’analyse en profondeur de textes. Dans ce papier, nous nous penchons sur le résumé automatique guidé de textes. Dans un premier temps, nous définissons les différentes caractéristiques et contraintes liées à cette tâche. Ensuite, nous dressons un état de l’art des principaux systèmes existants en mettant l’accent sur les travaux les plus récents, et en les classifiant selon les approches adoptées, les techniques utilisées, et leurs évaluations sur des corpus de références. Enfin, nous proposons les grandes étapes d’une méthode spécifique devant permettre le développement d’un nouveau type de systèmes de résumé guidé.

2017

pdf
UPC-USMBA at SemEval-2017 Task 3: Combining multiple approaches for CQA for Arabic
Yassine El Adlouni | Imane Lahbari | Horacio Rodríguez | Mohammed Meknassi | Said Ouatik El Alaoui | Noureddine Ennahnahi
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

This paper presents a description of the participation of the UPC-USMBA team in the SemEval 2017 Task 3, subtask D, Arabic. Our approach for facing the task is based on a combination of a set of atomic classifiers. The atomic classifiers include lexical string based, based on vectorial representations and rulebased. Several combination approaches have been tried.

pdf
A Biomedical Question Answering System in BioASQ 2017
Mourad Sarrouti | Said Ouatik El Alaoui
BioNLP 2017

Question answering, the identification of short accurate answers to users questions, is a longstanding challenge widely studied over the last decades in the open domain. However, it still requires further efforts in the biomedical domain. In this paper, we describe our participation in phase B of task 5b in the 2017 BioASQ challenge using our biomedical question answering system. Our system, dealing with four types of questions (i.e., yes/no, factoid, list, and summary), is based on (1) a dictionary-based approach for generating the exact answers of yes/no questions, (2) UMLS metathesaurus and term frequency metric for extracting the exact answers of factoid and list questions, and (3) the BM25 model and UMLS concepts for retrieving the ideal answers (i.e., paragraph-sized summaries). Preliminary results show that our system achieves good and competitive results in both exact and ideal answers extraction tasks as compared with the participating systems.