MSA

The KIND Dataset: A Social Collaboration Approach for Nuanced Dialect Data Collection (2024.eacl-srw)

Challenge:	Multimodal sentiment analysis (MSA) has gained much attention over the last few years due to a lack of unimodal annotations in benchmark datasets.
Approach:	They propose a framework which integrates multimodal and unimodal tasks to optimize learning representations from multimodal data.
Outcome:	The proposed model learns to weight features differently based on features of other modalities and auto-generates unimodal annotations via a unimodule.

Copied to clipboard

Asma Yamani, Raghad Alziyady, Reem AlYami, Salma Albelali, Leina Albelali, Jawharah Almulhim, Amjad Alsulami, Motaz Alfarraj, Rabeah Al-Zaidy

Machine Translation

Challenge:	Nuanced dialects are a linguistic variant that pose several challenges for NLP models and techniques.
Approach:	They propose an approach to collect high quality Arabic dialect data by social collaboration . they use short texts to collect Arabic dialects and a KIND corpus .
Outcome:	The proposed approach is based on the KIND corpus of Arabic dialect data . it provides a high quality dataset and is versatile enough to be multipurpose .

Sequential Fusion of Text-close and Text-far Representations for Multimodal Sentiment Analysis (2025.coling-main)

Copied to clipboard

Kaiwei Sun, Mi Tian

Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality (2022.aacl-main)

Challenge:	Multimodal Sentiment Analysis (MSA) aims to identify human attitudes from diverse modalities such as visual, audio and text.
Approach:	They propose a framework to combine text-close and text-far representations to refine multimodal representations from multimodal data.
Outcome:	The proposed framework explores similarities and differences between text and audio/visual modalities and fuses extracted representations more effectively.

Copied to clipboard

Haozhe Chi, Minghua Yang, Junhao Zhu, Guanhong Wang, Gaoang Wang

GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP (2023.emnlp-main)

Challenge:	Existing methods to address missing modalities often assume a particular modality is completely missing due to recording or transmission error.
Approach:	They propose a missing modality-based meta-sampling approach for multimodal sentiment analysis with missing modalities . they conduct experiments on IEMOCAP, SIMS and CMU-MOSI datasets .
Outcome:	The proposed method significantly improves on existing models with a mixture of missing modalities.

Copied to clipboard

Md Tawkat Islam Khondaker, Abdul Waheed, El Moatez Billah Nagoudi, Muhammad Abdul-Mageed

Dialogue Systems & Conversational Agents

Challenge:	Our study examines ChatGPT’s performance on Arabic languages and dialectal varieties.
Approach:	They conduct a large-scale automated and human evaluation of ChatGPT, encompassing 44 distinct language understanding and generation tasks on over 60 different datasets.
Outcome:	The proposed model outperforms smaller models on Arabic dialects compared to GPT-4's Modern Standard Arabic and Dialectal Arabic (DA)

ArMATH: a Dataset for Solving Arabic Math Word Problems (2022.lrec-1)

Copied to clipboard

Reem Alghamdi, Zhenwen Liang, Xiangliang Zhang

Numerical Reasoning

Challenge:	This paper is the first to use deep learning methods to solve Arabic MWPs . it is also the first study to use transfer learning to solve MWp across different languages .
Approach:	They contribute to the first large-scale dataset for Arabic Math Word Problems . they use deep learning methods to solve Arabic MWPs and a transfer learning model to promote performance .
Outcome:	The proposed model improves Arabic MWP solvers by 3% over the existing model.

A System for Diacritizing Four Varieties of Arabic (D19-3)

Copied to clipboard

Hamdy Mubarak, Ahmed Abdelali, Kareem Darwish, Mohamed Eldesouki, Younes Samih, Hassan Sajjad

Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis (2023.emnlp-main)

Challenge:	Short vowels, aka diacritics, are omitted when writing different varieties of Arabic . diacritization is essential for language learning and text-to-speech applications .
Approach:	They propose a system for recovering diacritics in Arabic without short vowels . they use a character-based sequence-to-sequence deep learning model .
Outcome:	The proposed system beats all previous SOTA systems for Arabic varieties . it uses a character-based sequence-to-sequence deep learning model .

Copied to clipboard

Haoyu Zhang, Yu Wang, Guanghao Yin, Kejun Liu, Yuanyuan Liu, Tianshu Yu

Analyzing Modality Robustness in Multimodal Sentiment Analysis (2022.naacl-main)

Challenge:	Multimodal Sentiment Analysis (MSA) is effective when using rich information from multiple sources, but the potential sentiment-irrelevant information across modalities may hinder the performance from being further improved.
Approach:	They propose an Adaptive Language-guided Multimodal Transformer (ALMT) that learns an irrelevance/conflict-suppressing representation from visual and audio features under guidance of language features at different scales.
Outcome:	The proposed model achieves state-of-the-art on several popular datasets and an abundance of ablation shows the effectiveness of the proposed model.

Copied to clipboard

Devamanyu Hazarika, Yingting Li, Bo Cheng, Shuai Zhao, Roger Zimmermann, Soujanya Poria

Self-Training Pre-Trained Language Models for Zero- and Few-Shot Multi-Dialectal Arabic Sequence Labeling (2021.eacl-main)

Challenge:	despite its importance, little attention has been paid to improving the robustness of multimodal models.
Approach:	They propose simple diagnostic checks for modality robustness in a trained multimodal model . they find MSA models highly sensitive to a single modality, which creates issues .
Outcome:	The proposed checks show that models are highly sensitive to a single modality, which creates issues in their robustness.

Copied to clipboard

Muhammad Khalifa, Muhammad Abdul-Mageed, Khaled Shaalan

Computational Morphology and Lexicography Modeling of Modern Standard Arabic Nominals (2024.findings-eacl)

Challenge:	Existing approaches to fine-tune pre-trained language models for downstream tasks require labeled data.
Approach:	They propose to self-train pre-trained language models to improve performance on data-scarce varieties by as large as 10% F1 and 2% accuracy.
Outcome:	The proposed model improves zero-shot MSA-to-DA transfer by as large as 10% F1 (NER) and 2% accuracy (POS tagging).

Copied to clipboard

Christian Khairallah, Reham Marzouk, Salam Khalifa, Mayar Nassar, Nizar Habash

Mixture of Multimodal Adapters for Sentiment Analysis (2025.naacl-long)

Challenge:	Modern Standard Arabic (MSA) nominals present many morphological and lexical modeling challenges that have not been consistently addressed before.
Approach:	They propose to use a morphological framework to model Arabic nominals using a proposed morphology framework.
Outcome:	The proposed model improves accuracy and consistency compared to a commonly used morphological analyzer and generator.

Copied to clipboard

Kezhou Chen, Shuo Wang, Huixia Ben, Shengeng Tang, Yanbin Hao

Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)

Challenge:	Pre-trained language models (PLMs) have been used for text sentiment analysis but sentiment is hidden in other modalities.
Approach:	They propose to fuse emotions from different data to analyze sentiments . they use compression parameter for each expert to reduce training burden .
Outcome:	The proposed method achieves state-of-the-art with a tiny trainable parameter count compared to current methods . emotions hidden in body movements or vocal timbres eclipse traditional methods compared with text sentiment analysis .

Copied to clipboard

Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Sheng Wang, Lingpeng Kong

Which is Making the Contribution: Modulating Unimodal and Cross-modal Dynamics for Multimodal Sentiment Analysis (2021.findings-emnlp)

Challenge:	Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited.
Approach:	They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning .
Outcome:	The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster.

Copied to clipboard

Ying Zeng, Sijie Mai, Haifeng Hu

Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs (2025.acl-long)

Challenge:	Recent studies focus on learning cross-modal dynamics, but neglect to explore optimal solution for unimodal networks.
Approach:	They propose a new MSA framework to identify contribution of modalities and reduce impact of noisy information.
Outcome:	The proposed model outperforms state-of-the-art methods on publicly available datasets.

Copied to clipboard

Yijie Jin, Junjie Peng, Xuanchao Lin, Haochen Yuan, Lan Wang, Cangzhi Zheng

Unsupervised Speech-text word-level alignment with Dynamic Programming (2025.findings-naacl)

Challenge:	Multimodal Sentiment Analysis (MSA) is a rapidly developing field that integrates multimodal information to recognize sentiments.
Approach:	They propose a multimodal fusion model that integrates multimodal information to recognize sentiments using multimodal transformers.
Outcome:	The proposed model achieves significantly higher performance than MulTs and the existing model is robust.

Copied to clipboard

Tianshu Yu, Zihan Gong, Minghuan Tan, Guhong Chen, Min Yang

Arabic Diacritization Using Morphologically Informed Character-Level Model (2024.lrec-main)

Challenge:	Word-level alignment in speech-text pretraining models is limited by word-level annotated data . authors propose an iterative training method for USDP that reduces the dependency on scarce annotation resources.
Approach:	They propose an Unsupervised Speech-text word-level alignment with Dynamic Programming (USDP) this method uses Dynamic programming principles to iteratively refine temporal alignment predictions .
Outcome:	The proposed method significantly improves on speech-text pretraining tasks compared to existing methods.

Copied to clipboard

Muhammad Morsy Elmallah, Mahmoud Reda, Kareem Darwish, Abdelrahman El-Sheikh, Ashraf Hatim Elneima, Murtadha Aljubran, Nouf Alsaeed, Reem Mohammed, Mohamed Al-Badrashiny

An Automatic Learning of an Algerian Dialect Lexicon by using Multilingual Word Embeddings (L18-1)

Challenge:	Diacritics are typically omitted in Arabic writings and the reader needs to guess the proper diacritics as they are reading.
Approach:	They propose a morphologically informed character-level model that can recover both types of diacritics simultaneously.
Outcome:	The proposed model achieves lowest word-level diacritization error rate for Classical Arabic, MSA, and two dialectal Arabic texts.

Copied to clipboard

Abidi Karima, Kamel Smaïli

CLGSI: A Multimodal Sentiment Analysis Framework based on Contrastive Learning Guided by Sentiment Intensity (2024.findings-naacl)

Challenge:	a study on the Algerian Arabic dialect aims to build a lexicon of words written in Arabic or Latin script . multilinguality of the corpus is due to the fact that people use several languages to post comments . stretched letters, misspelled words, emoticons, condensed writing are among the problems .
Approach:	They propose to build automatically from a social network an Algerian dialect lexicon.
Outcome:	The proposed method leads to a score of 73% on a test lexicon . the study is based on analyzing a lexical corpus of an Algerian dialect .

Copied to clipboard

Yang Yang, Xunde Dong, Yupeng Qiang

From Multiple-Choice to Extractive QA: A Case Study for English and Arabic (2025.coling-main)

Challenge:	Recent studies have focused on contrastive learning, but lack detailed learning of the distribution of sample pairs with different sentiment intensity differences in the contrastive training representation space.
Approach:	They propose a framework for multimodal sentiment analysis based on contrastive learning guided by sentiment intensity (CLGSI) it selects positive and negative sample pairs based upon sentiment intensity differences and assigns corresponding weights accordingly.
Outcome:	The proposed framework extracts common features between different modalities and then uses them to predict sentiment intensity.

Copied to clipboard

Teresa Lynn, Malik H. Altakrori, Samar M. Magdy, Rocktim Jyoti Das, Chenyang Lyu, Mohamed Nasr, Younes Samih, Kirill Chirkunov, Alham Fikri Aji, Preslav Nakov, Shantanu Godbole, Salim Roukos, Radu Florian, Nizar Habash

Question Answering

Challenge:	Recent years have brought about very fast developments in Natural Language Processing (NLP), but many other languages are overlooked due to limited resources.
Approach:	They propose to repurpose a multilingual BELEBELE dataset for a task of extractive QA in the style of machine reading comprehension.
Outcome:	The proposed approach could be used to extract QA in the style of machine reading comprehension.

Mitigating Inconsistencies in Multimodal Sentiment Analysis under Uncertain Missing Modalities (2022.emnlp-main)

Copied to clipboard

Jiandian Zeng, Jiantao Zhou, Tianyi Liu

Curriculum Learning Meets Weakly Supervised Multimodal Correlation Learning (2022.emnlp-main)

Challenge:	Existing studies ignore the inconsistency phenomenon of missing modality in multimodal sentiment analysis . neglect of missing modalities may lead to incorrect semantic results .
Approach:	They propose an ensemble-based Missing Modality Reconstruction network to detect and recover missing modality features.
Outcome:	The proposed method is superior to existing methods on CMU-MOSI and IEMOCAP datasets.

Copied to clipboard

Sijie Mai, Ya Sun, Haifeng Hu

LaCoMSA: Language-Consistency Multilingual Self-Alignment with Latent Representation Rewarding (2026.eacl-long)

Challenge:	Existing studies have used the correlation information stored in samples for self-supervised learning, but they feed the training pairs in a random order without consideration of difficulty.
Approach:	They propose to inject curriculum learning into weakly supervised multimodal correlation learning by scoring and feeding pairs according to difficulty.
Outcome:	The proposed model achieves state-of-the-art on multimodal sentiment analysis without human annotation.

Copied to clipboard

Khanh-Tung Tran, Barry O'Sullivan, Hoang D. Nguyen

Representation Learning

Challenge:	Existing multilingual alignment methods mitigate these issues but rely on external supervision, such as translation systems or English-biased signal.
Approach:	They propose a preference optimization framework that leverages an LLM’s own latent representations as intrinsic supervision signals and rewards lower-resource language outputs based on their alignment with high-resourced (English) counterparts in the "semantic hub".
Outcome:	The proposed framework improves a Llama 3 8B model multilingual win rates by up to 6.8% absolute (55.0% relative) on X-AlpacaEval and achieves consistent gains across benchmarks and models.

mABC: Multi-Agent Blockchain-inspired Collaboration for Root Cause Analysis in Micro-Services Architecture (2024.findings-emnlp)

Copied to clipboard

Wei Zhang, Hongcheng Guo, Jian Yang, Zhoujin Tian, Yi Zhang, Yan Chaoran, Zhoujun Li, Tongliang Li, Xu Shi, Liangfan Zheng, Bo Zhang

Uncertainty-Calibrated Elastic Alignment for Multimodal Sentiment Analysis with Missing Modalities (2026.findings-acl)

Challenge:	Root cause analysis (RCA) in Micro-services architectures with escalating complexity is challenging due to fault propagation and circular dependencies among nodes.
Approach:	They propose a framework where multiple agents follow Agent Workflow and collaborate in blockchain-inspired voting to ensure the reliability of root cause analysis.
Outcome:	The proposed framework reduces the number of steps and standardizes task processing through Agent Workflow.

Copied to clipboard

Kang He, Yuzhe Ding, Rao Fu, Yukang Feng, Kaipeng Zhang, Yiming Liu, Fei Li, Chong Teng, Donghong Ji

AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs (2025.coling-main)

Challenge:	Existing methods for multimodal sentiment analysis are often dynamically incomplete.
Approach:	They propose a new uncertainty-calibrated elastic alignment framework to address these issues by employing probabilistic imputation to capture cross-modal ambiguity and leverage the estimated uncertainty to drive elastic alignment.
Outcome:	The proposed framework outperforms state-of-the-art models in multiple benchmarks and consistently outperformed existing models.

Copied to clipboard

Basel Mousi, Nadir Durrani, Fatema Ahmad, Md. Arid Hasan, Maram Hasanain, Tameem Kabbani, Fahim Dalvi, Shammur Absar Chowdhury, Firoj Alam

Multilinguality

Challenge:	a recent study has found that Arabic is underrepresented in Large Language Models, especially in dialectal variations.
Approach:	They propose a benchmark for Arabic Dialect and Cultural Evaluation that evaluates Arabic dialect comprehension and generation.
Outcome:	The proposed model outperforms multilingual models on dialect comprehension and generation, but significant challenges persist in dialect identification, generation, and translation.

MPID: A Modality-Preserving and Interaction-Driven Fusion Network for Multimodal Sentiment Analysis (2025.coling-main)

Copied to clipboard

Tianyi Li, Daming Liu

Modal Feature Optimization Network with Prompt for Multimodal Sentiment Analysis (2025.coling-main)

Challenge:	Current methods for multimodal sensing analysis overlook nuanced differences and similarities across modalities, leading to potential biases.
Approach:	They propose a Modal-Preserving and Interaction-Driven Fusion Network to address these challenges by integrating text with audio and a separate Adaptive Graded Fusion Module for text and visual data.
Outcome:	The proposed model achieves state-of-the-art on CMU-MOSI, CMU -MOSEI, and CH-SIMS datasets.

Copied to clipboard

Xiangmin Zhang, Wei Wei, Shihao Zou

ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic (2024.findings-acl)

Challenge:	Multimodal sentiment analysis(MSA) is used to understand human emotional states through multimodal.
Approach:	They propose a Modal Feature Optimization Network with a modal prompt attention mechanism to optimize the under-optimized modal representation by determining which modalities are under- optimized .
Outcome:	The proposed method outperforms existing state-of-the-art models on public benchmark datasets.

Copied to clipboard

Fajri Koto, Haonan Li, Sara Shatnawi, Jad Doughman, Abdelrahman Sadallah, Aisha Alraeesi, Khalid Almubarak, Zaid Alyafeai, Neha Sengupta, Shady Shehata, Nizar Habash, Preslav Nakov, Timothy Baldwin

Challenge:	evaluating language models in Arabic remains challenging due to limited datasets . focus has shift to reasoning and knowledge-intensive tasks due to lack of relevant datasets.
Approach:	They propose to use ArabicMMLU to evaluate models' understanding of Arabic . they use 40 tasks and 14,575 multiple-choice questions from school exams in different countries .
Outcome:	The ArabicMMLU is the first multi-task language understanding benchmark for the Arabic language . it is based on 40 tasks and 14,575 multiple-choice questions in modern standard Arabic . the models are based in different countries across North Africa, the Levant, and the Gulf regions .

Cross-lingual Multimodal Sentiment Analysis for Low-Resource Languages via Language Family Disentanglement and Rethinking Transfer (2025.findings-acl)

Copied to clipboard

Long Chen, Shuoyu Guan, Xiaohua Huang, Wen-Jing Wang, Cai Xu, Ziyu Guan, Wei Zhao

Low-Resource NLP

Challenge:	Existing multimodal sentiment analysis methods are limited to textual data and cannot handle multimodal scenarios.
Approach:	They propose a transfer learning framework that allows cross-lingual and cross-modal alignments and a language family disentanglement module that enhances the sharing of language universals within families.
Outcome:	The proposed method is superior to existing methods and can handle low-resource languages.

Generative-to-Discriminative Test-Time Adaptation via Manifold-Aware Diffusion and Bayesian Distillation (2026.findings-acl)

Copied to clipboard

Boyun Zhang, Zequn Xie, Fangming Feng, Zihan Zhang, Yongbo He, Chuxin Wang, Sihang Cai, Tao Jin, Qifei Zhang

Commonsense Reasoning in Arab Culture (2025.acl-long)

Challenge:	Existing discriminative approaches suffer from "confident but wrong" failure mode, blindly adapting to OOD noise leading to error accumulation.
Approach:	They propose a TTA framework that harmonizes the robustness of generative diffusion models with the efficiency of discriminative regression networks via Bayesian Diffusion Distillation (BDD).
Outcome:	The proposed framework reduces MAE from 0.6872 to 0.5673 and boosts binary accuracy by 5.81 percentage points (reaching 57.33%) it also reduces the MAE of the MOSI to SIMS shift and achieves an 11.18-point gain over the baseline.

Copied to clipboard

Abdelrahman Sadallah, Junior Cedric Tonga, Khalid Almubarak, Saeed Almheiri, Farah Atif, Chatrine Qwaider, Karima Kadaoui, Sara Shatnawi, Yaser Alesh, Fajri Koto

Reasoning

Challenge:	Existing studies on commonsense reasoning in Arabic have relied on machine translations that lack cultural depth and introduce anglocentric biases.
Approach:	They propose a commonsense reasoning dataset in Arabic that covers 13 Arab countries.
Outcome:	The proposed dataset covers 13 countries across the Gulf, Levant, North Africa, and the Nile Valley.

Wojood: Nested Arabic Named Entity Corpus and Recognition using BERT (2022.lrec-1)

Copied to clipboard

Mustafa Jarrar, Mohammed Khalilia, Sana Ghanem

DET: A Dual-Encoding Transformer for Relational Graph Embedding (2024.lrec-main)

Challenge:	Named Entity Recognition (NER) is integral to many NLP applications such as chatbots and question answering.
Approach:	They propose to annotate Arabic nested entities instead of flat annotations by manually annotating 550K tokens with 21 entity types including person, organization, location, event and date.
Outcome:	The proposed model achieved an overall micro F1-score of 0.884 and the annotation guidelines and source code are publicly available.

Copied to clipboard

Lingbing Guo, Zhuo Chen, Jiaoyan Chen, Qiang Zhang, Huajun Chen

Cognate Transformer for Automated Phonological Reconstruction and Cognate Reflex Prediction (2023.emnlp-main)

Challenge:	Existing approaches to graph representation only consider the local neighbors, sacrificing the Transformer’s ability to attend to elements at any distance.
Approach:	They propose a dual-encoding Transformer architecture that uses a structural encoder and a semantic encoder to seek for semantically relevant nodes.
Outcome:	The proposed architecture achieves superior performance compared to state-of-the-art attention-based methods on complex relational graphs like KGs and citation networks.

Copied to clipboard

V.S.D.S.Mahesh Akavarapu, Arnab Bhattacharya

Fine-grained Artificial Neurons in Audio-transformers for Disentangling Neural Auditory Encoding (2023.findings-acl)

Challenge:	Phonological reconstruction is one of the central problems in historical linguistics where a proto-word of an ancestral language is determined from the observed cognate words of daughter languages.
Approach:	They propose to use a protein language model to train on multiple sequence alignments to train a model on phonological reconstruction.
Outcome:	The proposed model outperforms existing models on cognate reflex prediction task.

Copied to clipboard

Mengyue Zhou, Xu Liu, David Liu, Zihao Wu, Zhengliang Liu, Lin Zhao, Dajiang Zhu, Lei Guo, Junwei Han, Tianming Liu, Xintao Hu

Enhancing Deep Learning with Embedded Features for Arabic Named Entity Recognition (2022.lrec-1)

Challenge:	Existing studies treat each transformer encoding layer as a single artificial neuron . layer-level embeddings aggregate multiple types of contextual attention captured by multiple head modules .
Approach:	They propose to embed each transformer encoding layer as a single artificial neuron . they propose to couple those ANs with their biological-neuron counterparts in the human brain .
Outcome:	The proposed models can be used to link representations to brain activity, the authors say . their results show that the proposed models carry meaningful neurolinguistic information .

Copied to clipboard

Ali L. Hatab, Caroline Sabty, Slim Abdennadher

UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition (2022.emnlp-main)

Challenge:	Word embeddings can capture the semantics of words and other hidden features, but the Arabic language is complex and requires a large amount of information to process.
Approach:	They propose to add morphological and syntactical features to Arabic word embeddings to train the model.
Outcome:	The proposed model outperforms the previous systems to the best of our knowledge.

Copied to clipboard

Guimin Hu, Ting-En Lin, Yi Zhao, Guangming Lu, Yuchuan Wu, Yongbin Li

Dual-Path Dynamic Fusion with Learnable Query for Multimodal Sentiment Analysis (2025.emnlp-main)

Challenge:	Existing studies study sentiment and emotion separately and do not fully exploit the complementary knowledge behind the two.
Approach:	They propose a multimodal sentiment knowledge-sharing framework that unifies MSA and ERC tasks from features, labels, and models.
Outcome:	The proposed framework achieves consistent improvements on four public benchmark datasets on MOSI, MOSEI, MELD, and IEMOCAP.

Copied to clipboard

Miao Zhou, Lina Yang, Thomas Wu, Dongnan Yang, Xinru Zhang

Automatic Identification of Maghreb Dialects Using a Dictionary-Based Approach (L18-1)

Challenge:	Existing methods for multimodal sentiment analysis struggle with global and fine-grained contributions and over-reliance on text.
Approach:	They propose a multimodal sentiment analysis architecture that processes inputs through two complementary paths: global and local.
Outcome:	The proposed architecture achieves state-of-the-art in fine-grained sentiment prediction on the CMU-MOSI and CMU MOSEI benchmarks.

Copied to clipboard

Houda Saâdane, Hosni Seffih, Christian Fluhr, Khalid Choukri, Nasredine Semmar

Code-Switching

Challenge:	Automatic identification of Arabic dialects in texts is difficult, especially for Maghreb languages and when they are written in Arabic or Latin characters (Arabizi).
Approach:	They propose a dictionary-based approach to detect Arabic dialects in texts . they focus on transliteration of Arabicizi into Latin script and code-switching .
Outcome:	The proposed approach shows that it is possible to detect dialects in Arabic and Latin scripts.

Shami: A Corpus of Levantine Arabic Dialects (L18-1)

Copied to clipboard

Kathrein Abu Kwaik, Motaz Saad, Stergios Chatzikyriakidis, Simon Dobnik

Text Classification

Challenge:	Modern Standard Arabic is the official written language used in education and media . however, the spoken language varies widely across the Arab world .
Approach:	They construct a levantine dialect corpus covering data from four dialects spoken in four countries . they describe rules for pre-processing without affecting the meaning so that it is processable by NLP tools.
Outcome:	The proposed corpus is larger than existing corpora in terms of size, words and vocabularies.

Standardisation of Dialect Comments in Social Networks in View of Sentiment Analysis : Case of Tunisian Dialect (2022.lrec-1)

Copied to clipboard

Saméh Kchaou, Rahma Boujelbane, Emna Fsih, Lamia Hadrich-Belguith

Machine Translation

Challenge:	Using the internet, the spoken Arabic dialect language becomes informal languages written in social media . this linguistic situation inhibits mutual understanding and makes computational approaches difficult . we present a pipeline to standardize the written texts in social networks by translating them to MSA .
Approach:	They propose a pipeline to standardize Arabic written texts by translating them to MSA . they use a bert-based model to select Tunisian Dialect from MSA and other dialects .
Outcome:	The proposed pipeline achieves the best score for the standardization of written texts in social networks . the proposed pipeline includes the translated TD and the original text written in MSA .

TF-Mamba: Text-enhanced Fusion Mamba with Missing Modalities for Robust Multimodal Sentiment Analysis (2025.findings-emnlp)

Copied to clipboard

Xiang Li, Xianfu Cheng, Dezhuang Miao, Xiaoming Zhang, Zhoujun Li

Part-of-Speech Tagging for Arabic Gulf Dialect Using Bi-LSTM (L18-1)

Challenge:	Existing Transformer-based methods with missing modalities are difficult to use and have quadratic complexity.
Approach:	They propose a text-enhanced Fusion Mamba framework for robust MSA with missing modalities . a Text-aware Modality Enhancement module aligns and enriches non-text modality while reconstructing missing text semantics.
Outcome:	The proposed method is efficient under missing modalities and can be used in long-range modeling and multimodal fusion scenarios.

Copied to clipboard

Randah Alharbi, Walid Magdy, Kareem Darwish, Ahmed AbdelAli, Hamdy Mubarak

Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis (2022.coling-1)

Challenge:	Part-of-speech (POS) tagging is one of the most important building blocks in many natural language processing (NLP) applications.
Approach:	They propose to use a POS tagger for Arabic Gulf dialect to improve POS tagging accuracy.
Outcome:	The proposed POS tagger improves POS tagging accuracy for the Arabic Gulf dialect from 75% accuracy to 91% accuracy using a bi-LSTM labeler.

Copied to clipboard

Zijie Lin, Bin Liang, Yunfei Long, Yixue Dang, Min Yang, Min Zhang, Ruifeng Xu

AMOA: Global Acoustic Feature Enhanced Modal-Order-Aware Network for Multimodal Sentiment Analysis (2022.coling-1)

Challenge:	Existing studies in Multimodal Sentiment Analysis lack a mechanism to understand complex relations between different modalities.
Approach:	They propose a hierarchical graph contrastive learning framework for multimodal sentiment analysis that explores the relationships between modality representations.
Outcome:	The proposed framework outperforms the state-of-the-art in multimodal sentiment analysis on two benchmark datasets.

Copied to clipboard

Ziming Li, Yan Zhou, Weibo Zhang, Yaxin Liu, Chuanpeng Yang, Zheng Lian, Songlin Hu

Annotating Attribution Relations in Arabic (L18-1)

Challenge:	Existing methods treat three modal features equally, without distinguishing the importance of different modalities. Existing models split the video into frames, leading to missing the global acoustic information.
Approach:	They propose a global Acoustic feature enhanced Modal-Order-Aware network to address these problems.
Outcome:	The proposed model outperforms state-of-the-art models on two public datasets.

Copied to clipboard

Amal Alsaif, Tasniem Alyahya, Madawi Alotaibi, Huda Almuzaini, Abeer Algahtani

Challenge:	Current studies focus on using lexical terms in long texts to verify author identity.
Approach:	They propose to annotate attributed arguments to the source in Arabic news with required syntactical and semantic features with required features.
Outcome:	The proposed method is applied to Arabic news and is compared with existing tools and methods.

ALDi: Quantifying the Arabic Level of Dialectness of Text (2023.emnlp-main)

Copied to clipboard

Amr Keleg, Sharon Goldwater, Walid Magdy

Challenge:	Existing work on Dialect Identification (DI) on the sentence level has focused on binary tasks, whereas ALDi treats the task as binary.
Approach:	They propose a dataset which contains 127,835 sentences manually labeled with their level of dialectness.
Outcome:	The proposed model can identify dialectness on a range of other corpora, providing a more nuanced picture than traditional DI systems.

Arabic Speech Rhythm Corpus: Read and Spontaneous Speaking Styles (2020.lrec-1)

Copied to clipboard

Omnia Ibrahim, Homa Asadi, Eman Kassem, Volker Dellwo

Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis (2021.emnlp-main)

Challenge:	a corpus of Arabic speech recordings has been built to allow comparisons between Arabic and other languages.
Approach:	They propose to build a corpus of Arabic speech recordings that can be compared with other languages.
Outcome:	The proposed corpus can be used for forensic phonetic research and casework applications.

Copied to clipboard

Wei Han, Hui Chen, Soujanya Poria

Multimodal Invariant Sentiment Representation Learning (2025.findings-acl)

Challenge:	Existing work on multimodal sentiment analysis relies on back-propagated task loss or geometric property of feature spaces to produce favorable fusion results.
Approach:	They propose a framework which hierarchically maximizes the Mutual Information (MI) in unimodal input pairs and between multimodal fusion result and unimod input to maintain task-related information through multimodal integration.
Outcome:	The proposed framework maximizes the Mutual Information (MI) in unimodal input pairs and between multimodal fusion result and unimodulated input to maintain task-related information through multimodal integration.

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation (2026.findings-acl)

Challenge:	Existing methods for multimodal sensing ignore significant sentiment distribution imbalances and cross-modal sentiment conflicts, hindering performance improvement.
Approach:	They propose a method to learn stable multimodal invariant sentiment representations by incorporating distributional discrepancies and sentiment conflicts into the model training.
Outcome:	The proposed method improves MSA performance and achieves new state-of-the-art.

Copied to clipboard

Haonan Shangguan, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Feiliang Ren, Ge Yu

Information Retrieval

Challenge:	Current approaches for Multimodal Sentiment Analysis (MSA) rely on parameter-heavy LLMs for classification, overlooking multimodal sentiment reasoning generation in resource-limited environments.
Approach:	They propose a multimodal sentiment reasoning distillation model that employs a teacher-assistant-student paradigm to address deployment constraints in resource-limited environments.
Outcome:	The proposed model performs well on a resource-limited JMSRC task with only 3B parameters and shows generalization and interpretability.

InfoEnh: Towards Multimodal Sentiment Analysis via Information Bottleneck Filter and Optimal Transport Alignment (2024.lrec-main)

Copied to clipboard

Yifeng Xie, Zhihong Zhu, Xuan Lu, Zhiqi Huang, Haoran Xiong

Sentiment Knowledge Enhanced Self-supervised Learning for Multimodal Sentiment Analysis (2023.findings-acl)

Challenge:	Existing methods for multi-modal sentiment analysis have been developed to overcome these challenges.
Approach:	They propose a method that utilizes a masking technique as the bottleneck for information filtering and integrates all modalities into a common feature space via domain adaptation.
Outcome:	Extensive experiments on two benchmark MSA datasets show the proposed method performs better than baselines.

Copied to clipboard

Fan Qian, Jiqing Han, Yongjun He, Tieran Zheng, Guibin Zheng

Knowledge-Guided Dynamic Modality Attention Fusion Framework for Multimodal Sentiment Analysis (2024.findings-emnlp)

Challenge:	Existing studies have used general approaches to alleviate the overfitting of supervised models based on video data with sentiment annotations.
Approach:	They propose to capture common sentimental patterns in unlabeled videos using sentiment knowledge and non-verbal behavior to embed sentiment information into pre-trained multimodal representations.
Outcome:	The proposed model outperforms the baseline and achieves new State-Of-The-Art (SOTA) results.

Copied to clipboard

Xinyu Feng, Yuming Lin, Lihua He, You Li, Liang Chang, Ya Zhou

Advancing Vision-Language Models with Adapter Ensemble Strategies (2024.findings-emnlp)

Challenge:	Existing methods focus on equally treating the contribution of each modality or statically using text as the dominant modality to conduct interaction, which neglects the situation where each modal may become dominant.
Approach:	They propose a Knowledge-Guided Dynamic Modality Attention Fusion Framework (KuDA) that uses sentiment knowledge to guide the model dynamically selecting the dominant modality and adjusting the contributions of each modality.
Outcome:	The proposed model can be used to highlight the contribution of dominant modality through the correlation evaluation loss.

Copied to clipboard

Yue Bai, Handong Zhao, Zhe Lin, Ajinkya Kale, Jiuxiang Gu, Tong Yu, Sungchul Kim, Yun Fu

Cultural Benchmarking of LLMs in Standard and Dialectal Arabic Dialogues (2026.acl-long)

Challenge:	CLIP revolutes vision-language pretraining by using contrastive learning on paired web data.
Approach:	They propose to combine a "adapter ensemble" with traditional machine learning techniques to augment large-scale pretrained vision-language models.
Outcome:	The proposed model outperforms baselines and derives improvement when the number of ensemble parameters increases.

Copied to clipboard

Muhammad Dehan Al Kautsar, Saeed Almheiri, Momina Ahsan, Bilal Elbouardi, Younes Samih, Sarfraz Ahmad, Amr Keleg, Omar El Herraoui, Kareem Elzeky, Abed Alhakim Freihat, Mohamed Anwar, Zhuohan Xie, Junhong Liang, Mohammad Rustom Al Nasar, Preslav Nakov, Fajri Koto

Dialogue Systems & Conversational Agents

Challenge:	Most benchmarks focus on short text snippets in Modern Standard Arabic (MSA), overlooking cultural nuances that naturally arise in dialogues.
Approach:	They propose a culturally grounded conversational dataset covering 13 Arabic-speaking countries, in both Modern Standard Arabic (MSA) and each country’s respective dialect, spanning 12 daily-life topics and 54 fine-grained subtopics.
Outcome:	The proposed model performs worse on all three tasks than the MSA benchmark.

MARASTA: A Multi-dialectal Arabic Cross-domain Stance Corpus (2024.lrec-main)

Copied to clipboard

Anis Charfi, Mabrouka Ben-Sghaier, Andria Samy Raouf Atalla, Raghda Akasheh, Sara Al-Emadi, Wajdi Zaghouani

Mixture-of-Prompt-Experts for Multi-modal Semantic Understanding (2024.lrec-main)

Challenge:	Approximately half of the sentences are in Modern Standard Arabic (MSA) for each region, and the other half is in the region’s respective dialect.
Approach:	They propose a cross-domain and multi-dialectal stance corpus for Arabic that includes four regions in the Arab World and covers the main Arabic dialect groups.
Outcome:	The proposed corpus outperforms the state-of-the-art dataset in stance detection and dialect and dialect classes.

Copied to clipboard

Zichen Wu, Hsiu-Yuan Huang, Fanyi Qu, Yunfang Wu

Proxy-Driven Robust Multimodal Sentiment Analysis with Incomplete Data (2025.acl-long)

Challenge:	Multimodal semantic understanding is crucial for developing machines capable of interpreting complex interplay of text and visual information.
Approach:	They propose a multi-modal soft prompt framework that integrates three experts of soft prompts . they propose sarcasm detection and sentiment analysis tasks that are critical for few-shot learning .
Outcome:	The proposed model outperforms the 8.2B model InstructBLIP with 2% parameters . it significantly outperformed other prompt methods on VLMs or task-specific methods .

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

NeoAraBERT: A Modern Foundation Model for Arabic Embeddings with Diacritics-Aware Tokenization and POS-Targeted Masking (2026.findings-acl)

Challenge:	Existing studies focus on optimizing model structures to handle uncertain missingness, but models still face challenges when dealing with uncertain missing data.
Approach:	They propose a data-centric robust multimodal sentiment analysis method, Proxy-Driven Robust Multimodal Fusion, which maps unimodal data to the latent space of Gaussian distributions to capture core features and structure.
Outcome:	The proposed method outperforms existing models in noise resistance and achieves state-of-the-art performance on multiple benchmark datasets.

Copied to clipboard

Chadi Abou Chakra, Hadi Khaled Hamoud, Osama Rakan Al Mraikhat, Qusai Abu Obaida, Mohamad Ballout, Fadi Zaraket

Zero-Shot Context-Aware ASR for Diverse Arabic Varieties (2026.findings-acl)

Challenge:	NeoAraBERT is an open-source text-embedding model for Arabic.
Approach:	They propose to train Arabic text-embedding models on open-source datasets . they benchmarked NeoAraBERT against five top-performing Arabic models on 23 tasks .
Outcome:	The proposed model outperforms five other models on 23 tasks in Arabic . it shows substantial improvement on classical and modern standard Arabic compared to other models .

Copied to clipboard

Bashar Talafha, Amin Abu Alhassan, Muhammad Abdul-Mageed

Active Learning for Multidialectal Arabic POS Tagging (2025.findings-emnlp)

Challenge:	Large-scale multilingual ASR has substantially improved recognition for high-resource languages.
Approach:	They propose a proxy-guided -best selection paradigm that conditions inference on external side information without parameter updates.
Outcome:	The proposed model reduces WER by 15.6% relative and recovers a fraction of oracle n-best gains on the common voice MSA testbed.

Copied to clipboard

Diyam Akra, Mohammed Khalilia, Mustafa Jarrar

Dialectal Coverage And Generalization in Arabic Speech Recognition (2025.acl-long)

Challenge:	Multidialectal Arabic POS tagging is challenging due to the morphological richness and high variability among dialects.
Approach:	They propose an active learning approach for multidialectal Arabic POS tagging . they annotate approximately 15,000 tokens, reducing the annotation requirement by about 2,000 tokens .
Outcome:	The proposed approach achieves 97.6% accuracy on the Emirati corpus.

Copied to clipboard

Amirbek Djanibekov, Hawau Olamide Toyin, Raghad Alshalan, Abdullah Alatir, Hanan Aldarmaki

QA-MoE: Towards a Continuous Reliability Spectrum with Quality-Aware Mixture of Experts for Robust Multimodal Sentiment Analysis (2026.acl-long)

Challenge:	Existing ASR systems cover the modern standard Arabic variety but fail to cover the multitude of spoken variants.
Approach:	They propose a suite of automatic speech recognition models optimized to recognize multiple variants of spoken Arabic.
Outcome:	The proposed models show coverage and performance gains compared to prior models.

Copied to clipboard

Yitong Zhu, Yuxuan Jiang, Guanxuan Jiang, Bojing Hou, Peng Yuan Zhou, Ge Lin, Yuyang Wang

Alexandria: A Multi-Domain Dialectal Arabic Machine Translation Dataset for Culturally Inclusive and Linguistically Diverse LLMs (2026.acl-long)

Challenge:	Existing models that use multimodal inputs are often noisy or incomplete.
Approach:	They propose a Quality-Aware Mixture-of-Experts framework that quantifies modality reliability via aleatoric uncertainty.
Outcome:	The proposed framework is competitive or state-of-the-art across diverse degradation scenarios and exhibits a promising One-Checkpoint-for-all property in practice.

Copied to clipboard

Abdellah EL Mekki, Samar M. Magdy, Houdaifa Atou, Ruwa AbuHweidi, Baraah Qawasmeh, Omer Nacar, Thikra Al-hibiri, Razan Saadie, Hamzah A. Alsayadi, Nadia Ghezaiel Hammouda, Alshima Mohammed Alkhazimi, Aya Hamod, Al-Yas Yaqoob Al-Ghafri, Wesam El-Sayed, Asila Ismail al Sharji, Mohamad Ballout, Anas Belfathi, Karim Ghaddar, Serry Sibaee, Alaa Aoun, Aeej Mohammed Aseri, Lina Abureesh, Ahlam Bashiti, Majdal Yousef, Abdulaziz Hafiz, Yehdih Mohamed, Emira Hamedtou, Brakehe Emehah, Rahaf Alhamouri, Youssef Nafea, Aya El Aatar, Walid Al-Dhabyani, Emhemed S. Hamed, Sara Shatnawi, Fakhraddin Alwajih, Khalid Elkhidir, Ashwag Alasmari, Abdurrahman Gerrio, Omar Said Alshahri, AbdelRahim A. Elmadany, Ismail Berrada, Amir Azad Adli Al-kathiri, Fadi Zaraket, Mustafa Jarrar, Yahya Mohamed EL Hadj, Hassan Alhuzali, Muhammad Abdul-Mageed

Multilinguality

Challenge:	Arabic is a highly diglossic language where most daily communication occurs in regional dialects rather than modern standard Arabic (MSA).
Approach:	They propose a large-scale, community-driven, human-translated dataset to bridge this gap . Alexandria covers 13 Arab countries and 11 high-impact domains . it provides unprecedented granularity by associating contributions with city-of-origin metadata .
Outcome:	The Alexandria dataset covers 13 Arab countries and 11 high-impact domains . it provides unprecedented granularity by associating contributions with city-of-origin metadata . Alexandria is a training resource and a rigorous benchmark for evaluating MT and LLMs based on the Alexandria dataset .

DEAR: Distributional Error-Aware Reliability for Robust Multimodal Sentiment Analysis with Missing Modalities (2026.findings-acl)

Copied to clipboard

Shihao Zou, Wei Wei, Yongshuo Zhang

Fast Retrieval and Slow Reasoning for Explainable Multimodal Sentiment Analysis (2026.findings-acl)

Challenge:	Existing methods focus on feature completion but neglect semantic shifts caused by distribution gaps and decision risks under high uncertainty.
Approach:	They propose a distributional error-aware reliability estimation framework for robust MSA . they propose reconstructed features to be explicitly aligned with original distributional manifold .
Outcome:	The proposed framework mitigates semantic shifts by aligning reconstructed features with original distributional manifold . Extensive experiments on MOSI, MOSEI, and SIMS validate the framework .

Copied to clipboard

Aoqiang Zhu, Min Hu, Yan Xing