Program
Note: all times are in GMT+7
Friday August 16
(9:00 - 9:15) Welcome Speech
(9:15 - 10:30) Session 1: Core Technologies
Session Chair: Mustafa Jarrar
(09:15 - 09:30) - AREEj: Arabic Relation Extraction with Evidence
Osama Rakan Al Mraikhat, Hadi Khaled Hamoud, Fadi Zaraket(09:30 - 09:45) - A Context-Contrastive Inference Approach To Partial Diacritization
Muhammad ElNokrashy, Badr AlKhamissi(09:45 - 10:00) - Picking Up Where the Linguist Left Off:
Mapping Morphology to Phonology through Learning the Residuals
Salam Khalifa, Abdelrahim Qaddoumi, Ellen Broselow, Owen Rambow(10:00 - 10:15) - Event-Arguments Extraction Corpus and Modeling using BERT for Arabic
Alaa Aljabari, Lina Duaibes, Mustafa Jarrar, Mohammed Khalilia(10:15 - 10:30) - Exploiting Dialect Identification in Automatic Dialectal Text Normalization
Bashar Alhafni, Sarah Al-Towaity, Ziyad Fawzy, Fatema Nassar, Fadhl Eryani, Houda Bouamor, Nizar Habash
(10:30 - 11:00) Coffee Break
(11:00 - 11:45) Session 2: Downstream Applications I
Session Chair: Hamdy Mubarak
(11:00 - 11:15) - Strategies for Arabic Readability Modeling
Juan Pineros Liberato, Bashar Alhafni, Muhamed Osman Al Khalil, Nizar Habash(11:15 - 11:30) - Large Language Models as Legal Translators of Arabic Legislation:
Do ChatGPT and Gemini Care for Context and Terminology?
Khadija Ait ElFqih, Johanna Monti(11:30 - 11:45) - Arabic Automatic Story Generation with Large Language Models
Ahmed Oumar El-Shangiti, Fakhraddin Alwajih, Muhammad Abdul-Mageed
(11:45 - 12:30) Session 3: Multimodality
Session Chair: Salima Mdhaffar
(11:45 - 12:00) - AraCLIP: Cross-Lingual Learning for Effective Arabic Image Retrieval
Muhammad Al-Barham, Imad Afyouni, Khalid Almubarak, Ashraf Elnagar, Ayad Turky(12:00 - 12:15) - Towards Zero-Shot Text-To-Speech for Arabic Dialects
Khai Duy Doan, Abdul Waheed, Muhammad Abdul-Mageed(12:15 - 12:30) - Qalam: A Multimodal LLM for Arabic Optical Character and Handwriting Recognition
Gagan Bhatia, El Moatez Billah Nagoudi, Fakhraddin Alwajih, Muhammad Abdul-Mageed
(12:30 - 14:00) - Lunch Break + SIGARAB Business Meeting
(14:00 - 14:45) Session 4: Downstream Applications II
Session Chair: Ramy Eskander
(14:00 - 14:15) - ArabLegalEval: A Multitask Benchmark for Assessing Arabic Legal Knowledge in Large Language Models
Faris Hijazi, Somayah S Alharbi, Abdulaziz A. AlHussein, Harethah Abu Shairah, Reem Alzahrani, Hebah A. Alshamlan, George Turkiyyah, Omar Knio(14:15 - 14:30) - Benchmarking LLaMA-3 on Arabic Language Generation Tasks
Md Tawkat Islam Khondaker, Numaan Naeem, Fatimah Lyba Khan, AbdelRahim A. Elmadany, Muhammad Abdul-Mageed(14:30 - 14:45) - From Nile Sands to Digital Hands: Machine Translation of Coptic Texts
Muhammed Saeed, Asim Mohamed, Mukhtar Mohamed, Shady Shehata, Muhammad Abdul-Mageed
(14:45 - 15:15) Invited Talk: BALSAM: Community-Driven Arabic LLM Evaluation
(15:15 - 15:30) Shared Task Overview Boasters
(15:30 - 16:00) - Coffee Break
(16:00 - 17:30) Poster Session
Session Chair: Bashar Alhafni
(In-Person)
Wikidata as a Source of Demographic Information
Samir Abdaljalil, Hamdy MubarakImproving Language Models Trained with Translated Data via Continual Pre-Training and Dictionary Learning Analysis
Sabri Boughorbel, Md Rizwan Parvez, Majd HawaslyPerformance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect
Salima Mdhaffar, Haroun Elleuch, Fethi Bougares, Yannick EstèveAlclaM: Arabic Dialect Language Model
Murtadha Ahmed, Saghir Alfasly, Bo Wen, Jamal Addeen, MOHAMMED ABDELMAJEED M. AHMED, Yunfeng LiuJohn vs. Ahmed: Debate-Induced Bias in Multilingual LLMs
Anastasiia Demidova, Hanin atwany, Nour Rabih, Sanad Sha'ban, Muhammad Abdul-MageedOn the Utility of Pretraining Language Models on Synthetic Data
Alcides Alcoba Inciarte, Sang Yun Kwon, El Moatez Billah Nagoudi, Muhammad Abdul-MageedDallah: A Dialect-Aware Multimodal Large Language Model for Arabic
Fakhraddin Alwajih, Gagan Bhatia, Muhammad Abdul-MageedCATT: Character-based Arabic Tashkeel Transformer
Faris Alasmary, Orjuwan Zaafarani, Ahmad Ghannam
(Virtual)
Synthetic Arabic Medical Dialogues Using Advanced Multi-Agent LLM Techniques
Mariam ALMutairi, Lulwah AlKulaib, Melike Yildiz Aktas, Sara A. Alsalamah, Chang-Tien LuAuRED: Enabling Arabic Rumor Verification using Evidence from Authorities over Twitter
Fatima Haouari, Tamer Elsayed, Reem SuwailehData Augmentation for Speech-Based Diacritic Restoration
Sara Shatnawi, Sawsan Alqahtani, Shady Shehata, Hanan AldarmakiOut-of-Domain Dependency Parsing for Dialects of Arabic: A Case Study
Noor Abo Mokh, Daniel Dakota, Sandra KüblerInvestigating Linguistic Features for Arabic NLI
Yasmeen Bassas, Sandra KüblerQAES: First Publicly-Available Trait-Specific Annotations for Automated Scoring of Arabic Essays
May Bashendy, Salam Albatarni, Sohaila Eltanbouly, EMAN Zahran, Hamdo Elhuseyin, Tamer Elsayed, Walid Massoud, Houda BouamorFunctional Text Dimensions for Arabic Text Classification
Zeyd Ferhat, Abir Betka, Riyadh Barka, Zineddine Sarhani Kahhoul, Selma Boutiba, Mohamed Lakhdar Tiar, Habiba Dahmani, Ahmed Abdelali
(16:00 - 17:30) - Shared Task Papers (Posters)
(In-Person)
Upaya at ArabicNLU Shared-Task: Arabic Lexical Disambiguation using Large Language Models
ASOS at ArAIEval Shared Task: Integrating Text and Image Embeddings for Multimodal Propaganda Detection in Arabic Memes
Sina at FigNews 2024: Multilingual Datasets Annotated with Bias and Propaganda.
SQUad at FIGNEWS 2024 Shared Task: Unmasking Bias in Social Media Through Data Analysis and Annotation
Eagles at FIGNEWS 2024 Shared Task: A Context-informed Prescriptive Approach to Bias Detection in Contentious News Narratives
ASOS at KSAA-CAD 2024: One Embedding is All You Need for Your Dictionary
ASOS at NADI 2024 shared task: Bridging Dialectness Estimation and MSA Machine Translation for Arabic Language Enhancement
StanceCrafters at StanceEval2024: Multi-task Stance Detection using BERT Ensemble with Attention Based Aggregation
muNERa at WojoodNER 2024: Multi-tasking NER Approach
(Virtual)
Pirates at ArabicNLU2024: Enhancing Arabic Word Sense Disambiguation using Transformer-Based Approaches
rematchka at ArabicNLU2024: Evaluating Large Language Models for Arabic Word Sense and Location Sense Disambiguation
SMASH at AraFinNLP2024: Benchmarking Arabic BERT Models on the Intent Detection
Fired_from_NLP at AraFinNLP 2024: Dual-Phase-BERT - A Fine-Tuned Transformer-Based Model for Multi-Dialect Intent Detection in The Financial Domain for The Arabic Language
AlexuNLP24 at AraFinNLP2024: Multi-Dialect Arabic Intent Detection with Contrastive Learning in Banking Domain
SemanticCuetSync at AraFinNLP2024: Classification of Cross-Dialect Intent in the Banking Domain using Transformers
SENIT at AraFinNLP2024: trust your model or combine two
BabelBot at AraFinNLP2024: Fine-tuning T5 for Multi-dialect Intent Detection with Synthetic Data and Model Ensembling
MA at AraFinNLP2024: BERT-based Ensemble for Cross-dialectal Arabic Intent Detection
BFCI at AraFinNLP2024: Support Vector Machines for Arabic Financial Text Classification
dzFinNlp at AraFinNLP: Improving Intent Detection in Financial Conversational Agents
MemeMind at ArAIEval Shared Task: Generative Augmentation and Feature Fusion for Multimodal Propaganda Detection in Arabic Memes through Advanced Language and Vision Models
Mela at ArAIEval Shared Task: Propagandistic Techniques Detection in Arabic with a Multilingual Approach
MODOS at ArAIEval Shared Task: Multimodal Propagandistic Memes Classification Using Weighted SAM, CLIP and ArabianGPT
Nullpointer at ArAIEval Shared Task: Arabic Propagandist Technique Detection with Token-to-Word Mapping in Sequence Tagging
MemeMind at ArAIEval Shared Task: Spotting Persuasive Spans in Arabic Text with Persuasion Techniques Identification
CLTL at ArAIEval Shared Task: Multimodal Propagandistic Memes Classification Using Transformer Models
CUET_sstm at ArAIEval Shared Task: Unimodal (Text) Propagandistic Technique Detection Using Transformer-Based Model
AlexUNLP-MZ at ArAIEval Shared Task: Contrastive Learning, LLM Features Extraction and Multi-Objective Optimization for Arabic Multi-Modal Meme Propaganda Detection
SemanticCuetSync at ArAIEval Shared Task: Detecting Propagandistic Spans with Persuasion Techniques Identification using Pre-trained Transformers
SussexAI at ArAIEval Shared Task: Mitigating Class Imbalance in Arabic Propaganda Detection
Narrative Navigators at FIGNEWS 2024 Shared Task: New Frontiers in Bias and Propaganda Annotation Techniques
DRAGON at FIGNEWS 2024 Shared Task: a Dedicated RAG for October 7th conflict News
LexiconLadies at FIGNEWS 2024 Shared Task: Identifying Keywords for Bias Annotation Guidelines of Facebook News Headlines on the Israel-Palestine 2023 War
Uot1 at FIGNEWS 2024 Shared Task: Labeling News Bias
NLPColab at FigNews 2024 Shared Task: Challenges in Bias and Propaganda Annotation for News Media
Bias Bluff Busters at FIGNEWS 2024 Shared Task: Developing Guidelines to Make Bias Conscious
Ceasefire at FIGNEWS 2024 Shared Task: Automated Detection and Annotation of Media Bias Using Large Language Models
Sahara Pioneers at FIGNEWS 2024 Shared Task: Data Annotation Guidelines for Propaganda Detection in News Items
BiasGanda at FIGNEWS 2024 Shared Task: A Quest to Uncover Biased Views in News Coverage
The CyberEquity Lab at FIGNEWS 2024 Shared Task: Annotating a Corpus of Facebook Posts to Label Bias and Propaganda in Gaza-Israel War Coverage in Five Languages
BSC-LANGTECH at FIGNEWS 2024 Shared Task: Exploring Semi-Automatic Bias Annotation using Frame Analysis
GroningenAnnotatesGaza at the FIGNEWS 2024 Shared Task: Analyzing Bias in Conflict Narratives
JusticeLeague at FIGNEWS 2024 Shared Task: Innovations in Bias Annotation
The Guidelines Specialists at FIGNEWS 2024 Shared Task: An annotation guideline to Unravel Bias in News Media Narratives Using a Linguistic Approach
Cher at KSAA-CAD 2024: Compressing Words and Definitions into the Same Space for Arabic Reverse Dictionary
MISSION at KSAA-CAD 2024: AraT5 with Arabic Reverse Dictionary
Baleegh at KSAA-CAD 2024: Towards Enhancing Arabic Reverse Dictionaries
Arabic Train at NADI 2024 shared task: LLMs’ Ability to Translate Arabic Dialects into Modern Standard Arabic
AlexUNLP-STM at NADI 2024 shared task: Quantifying the Arabic Dialect Spectrum with Contrastive Learning, Weighted Sampling, and BERT-based Regression Ensemble
NLP_DI at NADI 2024 shared task: Multi-label Arabic Dialect Classifications with an Unsupervised Cross-Encoder
dzNLP at NADI 2024 Shared Task: Multi-Classifier Ensemble with Weighted Voting and TF-IDF Features
ELYADATA at NADI 2024 shared task: Arabic Dialect Identification with Similarity-Induced Mono-to-Multi Label Transformation.
Alson at NADI 2024 shared task: Alson - A fine-tuned model for Arabic Dialect Translation
CUFE at NADI 2024 shared task: Fine-Tuning Llama-3 To Translate From Arabic Dialects To Modern Standard Arabic
Team_Zero at StanceEval2024: Frozen PLMs for Arabic Stance Detection
ANLP RG at StanceEval2024: Comparative Evaluation of Stance, Sentiment and Sarcasm Detection
dzStance at StanceEval2024: Arabic Stance Detection based on Sentence Transformers
SMASH at StanceEval 2024: Prompt Engineering LLMs for Arabic Stance Detection
CUFE at StanceEval2024: Arabic Stance Detection with Fine-Tuned Llama-3 Model
MGKM at StanceEval2024 Fine-Tuning Large Language Models for Arabic Stance Detection
AlexUNLP-BH at StanceEval2024: Multiple Contrastive Losses Ensemble Strategy with Multi-Task Learning For Stance Detection in Arabic
Rasid at StanceEval: Fine-tuning MARBERT for Arabic Stance Detection
ISHFMG_TUN at StanceEval: Ensemble Method for Arabic Stance Evaluation System
PICT at StanceEval2024: Stance Detection in Arabic using Ensemble of Large Language Models
TAO at StanceEval2024 Shared Task: Arabic Stance Detection using AraBERT
Addax at WojoodNER 2024: Attention-Based Dual-Channel Neural Network for Arabic Named Entity Recognition
DRU at WojoodNER 2024: A Multi-level Method Approach
Bangor University at WojoodNER 2024: Advancing Arabic Named Entity Recognition with CAMeLBERT-Mix
DRU at WojoodNER 2024: ICL LLM for Arabic NER
mucAI at WojoodNER 2024: Arabic Named Entity Recognition with Nearest Neighbor Search
Speaker: Dr. Kareem Darwish, aiXplain
Bio: Dr. Kareem Darwish is a principal scientist with a joint appointment at QCRI and aiXplain Inc working on efficient human-in-the-loop ML, speech processing, and Large Language Models (LLMs). Previously, he was the acting research director of the Arabic Language Technologies group (ALT) at the Qatar Computing Research Institute (QCRI) where he worked on information retrieval, computational social science, and natural language processing. Kareem Darwish worked as a researcher at the Cairo Microsoft Innovation Lab and the IBM Human Language Technologies group in Cairo. He also taught at the German University in Cairo and Cairo University.
His research on natural language processing has led to state-of-the-art tools for Arabic processing that perform several tasks such as part-of-speech tagging, named entity recognition, automatic diacritic recovery, sentiment analysis, and parsing. His work on social computing focused on predictive stance detection to predict how users feel about an issue now or perhaps in the future, and on detecting malicious behavior on social media platform, particularly propaganda accounts. His innovative work on social computing has received much media coverage from international news outlets such as CNN, Newsweek, Washington Post, the Mirror, and many others.
Aside from the many research papers that he authored, he also authored books in both English and Arabic on a variety of subjects including Arabic processing, politics, and social psychology. He also has a YouTube channel dedicated to social psychology.