Topics ›
Natural language processing research from GCC institutions, covering Arabic NLP, multilingual models, text classification, named entity recognition, and machine translation.
351–400 articles · Page 8 RSS ↗
The paper introduces Duet, a hybrid neural relation understanding method for cardinality estimation. Duet addresses limitations of existing learned methods, such as high costs and scalability issues, by incorporating predicate information into an autoregressive model. Experiments demonstrate Duet's efficiency, accuracy, and scalability, even outperforming GPU-based methods on CPU.
Qatar Computing Research Institute (QCRI) published a paper in the Royal Society Open Science journal focusing on the role of "affective features" in improving Arabic dialect identification. The research demonstrates that incorporating features related to emotions and sentiment enhances the accuracy of identifying different Arabic dialects. The study used a dataset of 14 Levantine dialects. Why it matters: This highlights the growing focus on nuanced Arabic NLP research within the GCC, moving beyond standard language models to incorporate cultural and emotional understanding.
This paper evaluates the performance of GPT-3.5 and GPT-4 on seven Arabic NLP tasks including sentiment analysis, translation, and diacritization. GPT-4 outperforms GPT-3.5 on most tasks. The study provides an analysis of sentiment analysis and introduces a Python interface, Taqyim, for evaluating Arabic NLP tasks. Why it matters: The evaluation of LLMs on Arabic NLP tasks helps to identify strengths and weaknesses, guiding future research and development efforts in the field.
The paper introduces the Unscented Autoencoder (UAE), a novel deep generative model based on the Variational Autoencoder (VAE) framework. The UAE uses the Unscented Transform (UT) for a more informative posterior representation compared to the reparameterization trick in VAEs. It replaces Kullback-Leibler (KL) divergence with the Wasserstein distribution metric and demonstrates competitive performance in Fréchet Inception Distance (FID) scores.
This paper benchmarks the performance of OpenAI's Whisper model on diverse Arabic speech recognition tasks, using publicly available data and novel dialect evaluation sets. The study explores zero-shot, few-shot, and full finetuning scenarios. Results indicate that while Whisper outperforms XLS-R models in zero-shot settings on standard datasets, its performance drops significantly when applied to unseen Arabic dialects.
This paper introduces a new task: detecting propaganda techniques in code-switched text. The authors created and released a corpus of 1,030 English-Roman Urdu code-switched texts annotated with 20 propaganda techniques. Experiments show the importance of directly modeling multilinguality and using the right fine-tuning strategy for this task.
KAUST · · Healthcare Research
Researchers from KAUST, King Abdulaziz University, and King Abdulaziz University Hospital conducted a study comparing stem cells from Saudi Klinefelter patients with those from North American and European descent. Klinefelter syndrome affects approximately one in 600 Saudi males, but the MENA population is underrepresented in genomic studies of the disease. The study found a subset of genes on the X chromosome whose dysregulation characterizes Klinefelter syndrome, regardless of geographic origin or ethnicity. Why it matters: This research addresses a gap in understanding the molecular basis of Klinefelter syndrome in the MENA population and provides a platform for further studies of chromosomal diseases.
A new dataset called the Saudi Privacy Policy Dataset is introduced, which contains Arabic privacy policies from various sectors in Saudi Arabia. The dataset is annotated based on the 10 principles of the Personal Data Protection Law (PDPL) and includes 1,000 websites, 4,638 lines of text, and 775,370 tokens. The dataset aims to facilitate research and development in privacy policy analysis, NLP, and machine learning applications related to data protection.
KAUST · · Research Healthcare
KAUST researchers developed a new model integrating SIR compartment modeling in time and a point process modeling approach in space-time, also considering age-specific contact patterns. They used a two-step framework to model infectious locations over time for different age groups. The model demonstrated improved predictive accuracy in simulations and a COVID-19 case study in Cali, Colombia, compared to existing models. Why it matters: This model can assist decision-makers in identifying high-risk locations and vulnerable populations for better disease control strategies in the region and globally.
This paper introduces a mutually-regularized dual collaborative variational auto-encoder (MD-CVAE) for recommendation systems, addressing the limitations of user-oriented auto-encoders (UAEs) in handling sparse ratings and new items. MD-CVAE integrates item content and user ratings within a variational framework, regularizing UAE weights with item content to avoid non-optimal convergence. A symmetric inference strategy eliminates the need for retraining when introducing new items, enhancing efficiency in dynamic recommendation scenarios. Why it matters: The MD-CVAE approach offers a practical solution for improving recommendation accuracy and efficiency, especially in scenarios with data sparsity and frequent item updates, relevant to e-commerce and content platforms in the Middle East.
This paper presents six experiments evaluating personalization and user tracking in web search engine results. The experiments involve comparing search results based on VPN location (including UAE vs others), logged-in status, network type, search engine, browser, and trained Google accounts. The study measures total hits, first hit, and correlation between hits to identify patterns of personalization. Why it matters: The findings shed light on the extent of filter bubble effects and potential biases in search results for users in the UAE and globally.
Qatar Computing Research Institute (QCRI) is hosting a workshop focusing on the role of precision technologies and AI in advancing sustainable development goals. The workshop aims to explore how AI can optimize resource management, improve environmental monitoring, and enhance the efficiency of sustainable practices. It will bring together researchers, policymakers, and industry experts to discuss challenges and opportunities in leveraging AI for sustainability. Why it matters: This workshop highlights the increasing focus on using AI to address critical sustainability challenges in the region and globally.
This paper presents a benchmark study of contrastive learning (CL) methods applied to Arabic social meaning tasks like sentiment analysis and dialect identification. The study compares state-of-the-art supervised CL techniques against vanilla fine-tuning across a range of tasks. Results indicate that CL methods outperform vanilla fine-tuning in most cases and demonstrate data efficiency. Why it matters: This work highlights the potential of contrastive learning for improving performance in Arabic NLP, especially in low-resource scenarios.
The third Nuanced Arabic Dialect Identification Shared Task (NADI 2022) focused on advancing Arabic NLP through dialect identification and sentiment analysis at the country level. A total of 21 teams participated, with the winning team achieving 27.06 F1 score on dialect identification and 75.16 F1 score on sentiment analysis. The task highlights the challenges in Arabic dialect processing and motivates further research. Why it matters: Standardized evaluations like NADI are crucial for benchmarking progress and fostering innovation in Arabic NLP, especially for dialectal variations.
Researchers have developed Masader Plus, a web interface for browsing the Masader catalog of Arabic NLP datasets. The interface allows for data exploration, filtration, and API access to examine datasets. User interactions with the website are intended to provide a way to improve the dataset catalog itself. Why it matters: This interface lowers the barrier to entry for researchers seeking Arabic NLP datasets, facilitating more research in the field.
WAM News · · Partnership NLP
The Emirates News Agency (WAM) and Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) have signed a strategic partnership. The collaboration aims to advance knowledge and scientific research in AI, particularly in media. It will focus on developing innovative AI applications to enhance news content and delivery. Why it matters: This partnership signifies a growing trend of integrating AI into media in the UAE, potentially improving the quality and efficiency of news dissemination.
This paper introduces two shared tasks for abusive and threatening language detection in Urdu, a low-resource language with over 170 million speakers. The tasks involve binary classification of Urdu tweets into Abusive/Non-Abusive and Threatening/Non-Threatening categories, respectively. Datasets of 2400/6000 training tweets and 1100/3950 testing tweets were created and manually annotated, along with logistic regression and BERT-based baselines. 21 teams participated and the best systems achieved F1-scores of 0.880 and 0.545 on the abusive and threatening language tasks, respectively, with m-BERT showing the best performance.
This paper provides an overview of the UrduFake@FIRE2021 shared task, which focused on fake news detection in the Urdu language. The task involved binary classification of news articles into real or fake categories using a dataset of 1300 training and 300 testing articles across five domains. 34 teams registered, with 18 submitting results and 11 providing technical reports detailing various approaches from BoW to Transformer models, with the best system achieving an F1-macro score of 0.679.
The UrduFake@FIRE2021 shared task focused on fake news detection in the Urdu language, framed as a binary classification problem. 34 teams registered, with 18 submitting results and 11 providing technical reports, showcasing diverse approaches. The top-performing system utilized the stochastic gradient descent (SGD) algorithm, achieving an F-score of 0.679.
Researchers presented a study on using Artificial Intelligence for rapid damage assessment following disasters. The method leverages data from microblogs, such as social media platforms, to quickly identify and categorize damage. This approach aims to provide timely information for emergency response efforts and humanitarian aid. Why it matters: This research offers a critical tool for improving the efficiency and speed of disaster relief operations by harnessing widely available social media data.
arXiv · · NLP Healthcare
Researchers developed COVIBOT, a smart chatbot to spread awareness and assist during the COVID-19 pandemic in Saudi Arabia. The chatbot uses Azure Cognitive Services and is available in both English and Arabic. COVIBOT's use cases were tested and validated using a scenario-based approach.
Qatar Foundation · · Arabic AI NLP
MIT Technology Review reports on advancements in machine learning techniques that are significantly improving Arabic speech transcription capabilities. These developments aim to enhance the accuracy and robustness of Automatic Speech Recognition (ASR) systems for the complexities of the Arabic language, including its various dialects. The improvements are designed to overcome previous challenges in processing diverse phonetic patterns and linguistic nuances. Why it matters: This progress is vital for the development of more effective voice-enabled technologies, accessibility tools, and AI applications specifically tailored for Arabic-speaking populations in the Middle East and beyond.
The paper examines the performance of pre-trained Arabic language models on Arabic text intentionally stripped of diacritical dots to evade content classification. It proposes methods to support these "undotted" texts without retraining the models. The proposed methods achieve nearly perfect performance on one downstream task. Why it matters: The research highlights a vulnerability in Arabic NLP and offers solutions to maintain performance in the face of adversarial text manipulation.
This paper presents a comparative study of pre-trained transformer models for Arabic question answering (QA). The study evaluates the performance of AraBERTv2-base, AraBERTv0.2-large, and AraELECTRA models on four reading comprehension datasets: Arabic-SQuAD, ARCD, AQAD, and TyDiQA-GoldP. The researchers fine-tuned these models and analyzed the results to understand the performance disparities. Why it matters: This research contributes to the advancement of Arabic NLP by evaluating and comparing state-of-the-art models on important QA tasks, addressing the scarcity of resources in this domain.
Researchers created Masader, the largest public catalog for Arabic NLP datasets, containing 200 datasets annotated with 25 attributes. They developed a metadata annotation strategy applicable to other languages. The paper highlights issues within current Arabic NLP datasets and suggests recommendations. Why it matters: This curated dataset directory helps lower the barrier to entry for Arabic NLP research and development.
KAUST organized an Arabic Sentiment Analysis Challenge where participants developed ML models to classify tweets as positive, negative, or neutral. The competition used the ASAD dataset with 55K tweets for training, 20K for validation, and 20K for final evaluation. The full dataset of 100K labeled tweets has been released for public use.
This paper surveys machine learning approaches using monument pictures for analyzing heritage sites in India. It addresses challenges in the tourism sector, such as the unavailability of trained personnel and the lack of accurate information. The research aims to provide insights for building an automated decision system to modernize the tourism experience for visitors in India.
arXiv · · Healthcare Research
This paper examines the relationship between COVID-19 spread and weather patterns across 89 cities in Saudi Arabia using machine learning. The study uses daily COVID-19 case reports from the Saudi Ministry of Health and historical weather data. The results indicate that temperature and wind speed have the strongest correlation with the spread of COVID-19, with a random forest model achieving the best performance.
This paper focuses on analyzing surveys of women entrepreneurs in the UAE using machine learning techniques. The goal is to extract relevant insights from the data to understand the current landscape and predict future trends. The study aims to support better business decisions related to women in entrepreneurship.
This paper presents team SPPU-AASM's hybrid model for Arabic sarcasm and sentiment detection in the WANLP ArSarcasm shared task 2021. The model combines sentence representations from AraBERT with static word vectors trained on Arabic social media corpora. Results show the system achieves an F1-sarcastic score of 0.62 and a F-PN score of 0.715, outperforming existing approaches. Why it matters: The research demonstrates that combining context-free and contextualized representations improves performance in nuanced Arabic NLP tasks like sarcasm and sentiment analysis.
Researchers studied user lifetime prediction in the location-based social network Jodel within Saudi Arabia, leveraging its disjoint communities. Machine learning models, particularly Random Forest, were trained to predict user lifetime as a regression and classification problem. A single countrywide model generalizes well and performs similarly to community-specific models.
arXiv · · Healthcare Research
This study investigates the correlation between Google Trends data for COVID-19 symptoms and the actual number of COVID-19 cases in Saudi Arabia between March and October 2020. The researchers found that searches for "cough" and "sore throat" were most frequent, while "loss of smell", "loss of taste", and "diarrhea" showed the highest correlation with confirmed cases. The study concludes that Google searches can serve as a supplementary surveillance tool for monitoring the spread of COVID-19 in Saudi Arabia. Why it matters: The research demonstrates the potential of using readily available digital data to augment traditional surveillance methods for public health monitoring in the region.
This survey paper reviews the landscape of Natural Language Processing (NLP) research and applications in the Arab world. It discusses the unique challenges posed by the Arabic language, such as its morphological complexity and dialectal diversity. The paper also presents a historical overview of Arabic NLP and surveys various research areas, including machine translation, sentiment analysis, and speech recognition. Why it matters: The survey provides a comprehensive resource for researchers and practitioners interested in the current state and future directions of Arabic NLP, a field critical for enabling AI technologies to serve Arabic-speaking communities.
Researchers introduce ASAD, a new large-scale, high-quality Arabic Sentiment Analysis Dataset based on 95K tweets with positive, negative, and neutral labels. The dataset is launched with a competition sponsored by KAUST offering a total of 17000 USD in prizes. Baseline models are implemented and results reported to provide a reference for competition participants.
The Inception Team presented a system for Semantic Question Similarity in Arabic as part of the NSURL 2019 Task 8. The system explores different methods for determining question similarity in Arabic. Their best result was an ensemble model using a pre-trained multilingual BERT model, achieving a 95.924% F1-Score and ranking first among nine participating teams. Why it matters: This demonstrates strong performance on a key Arabic NLP task, advancing the state-of-the-art in semantic understanding for the language.
KAUST Associate Professor Xiangliang Zhang is using machine learning to analyze social media posts on Twitter related to COVID-19. Her team at KAUST's Computational Bioscience Research Center is analyzing sentiment in tweets using hashtags like #coronavirus and #covid19. Zhang aims to use this data to help predict localized outbreaks and provide an early warning system for governments and organizations. Why it matters: This research demonstrates the potential of AI-powered sentiment analysis to support public health efforts and inform decision-making during pandemics in the Middle East and globally.
KAUST · · Research Healthcare
KAUST researchers organized a week-long workshop on bioinformatics, covering genomics and transcriptomics data analysis. The workshop targeted students, postdocs, and senior researchers, providing hands-on training in coding and analysis using tools like R, Python, and shell scripts. Attendees with little prior computational biology experience were introduced to fundamental concepts and tools for handling large sequencing datasets. Why it matters: The workshop addresses the increasing need for bioinformatics expertise at KAUST and in the region, crucial for advancing research in fields like evolution and complex diseases.
KAUST · · Research Partnership
KAUST Ph.D. students Kai Lu and Yuqing Chen won Best Presentation awards at a Society of Exploration Geophysicists workshop in Beijing. Lu's research focuses on machine learning applications in seismic processing, while Chen uses machine learning for automated semblance spectrum picking. They both leverage KAUST's Shaheen II supercomputer for their work. Why it matters: This highlights the increasing role of AI and ML in the oil and gas industry, and KAUST's contribution to advancing these technologies.
KAUST Ph.D. student Adel Bibi is researching how to bridge the gap between theory and practice in deep learning, focusing on the mathematical understanding of deep learning models. Bibi is currently interning at Intel in Munich and previously worked on various computer vision problems. He aims to use optimization and mathematics to better understand deep learning models and build better models systematically from theory. Why it matters: This research contributes to the fundamental understanding of deep learning, potentially leading to more efficient and reliable AI systems developed in the region.
KAUST · · Healthcare Research
KAUST's Computational Bioscience Research Center (CBRC) and King Abdulaziz City for Science and Technology (KACST) have collaborated on research into methicillin-resistant Staphylococcus aureus (MRSA) within Saudi Arabia, starting in July 2018. The two-year project aims to understand MRSA drug resistance mechanisms specific to the Kingdom and its regions, with the goal of developing public health strategies. The project involves sequencing samples and performing bioinformatics analysis to support a network of researchers in the country. Why it matters: This initiative enhances Saudi Arabia's capacity to predict, prevent, and control infectious diseases, aligning with national health objectives and building local expertise in computational bioscience.
Lucidya, a startup founded by Saudi entrepreneurs including KAUST alumnus Zuhair Khayyat, utilizes AI and Big Data to analyze social media content from platforms like Twitter and Facebook, as well as articles from 200 million websites in over 120 languages. The technology predicts user emotions, detects interests, and provides content analyses to customers for better decision-making. Lucidya commercially transformed the scientific research 'Tagreed' to start their company. Why it matters: This demonstrates the growing potential of Saudi startups in leveraging AI for data analysis and social media monitoring, and it showcases the role of KAUST in fostering technological innovation and entrepreneurship within the Kingdom.
KAUST · · Research Partnership
KAUST held a research workshop on Optimization and Big Data, gathering researchers to discuss challenges and opportunities in the field. Speakers presented novel optimization algorithms and distributed systems for handling large datasets. The workshop featured 20 speakers from KAUST, global universities, and Microsoft Research. Why it matters: The event highlights KAUST's role as a regional hub for advancing research and development in big data and optimization, crucial for AI and various computational fields.
This paper explores language-independent alternatives to morphological segmentation for Arabic NLP using data-driven sub-word units, characters as a unit of learning, and word embeddings learned using a character CNN. The study evaluates these methods on machine translation and POS tagging tasks. Results show these methods achieve performance close to or surpassing state-of-the-art approaches. Why it matters: By offering simpler, more adaptable segmentation techniques, this research can help improve Arabic NLP applications across diverse domains and dialects.
This paper describes the MIT-QCRI team's Arabic Dialect Identification (ADI) system developed for the 2017 Multi-Genre Broadcast challenge (MGB-3). The system aims to distinguish between four major Arabic dialects and Modern Standard Arabic. The research explores Siamese neural network models and i-vector post-processing to handle dialect variability and domain mismatches, using both acoustic and linguistic features. Why it matters: The work contributes to the advancement of Arabic language processing, specifically in dialect identification, which is crucial for analyzing and understanding diverse Arabic speech content in media broadcasts.
arXiv · · Healthcare NLP
The paper introduces Guided Deep List, a tool for automating the generation of epidemiological line lists from open source reports. The tool uses distributed vector representations and dependency parsing to extract tabular data on disease outbreaks. It was evaluated on MERS outbreak data in Saudi Arabia, demonstrating improved accuracy over baseline methods and enabling epidemiological inferences.
This paper describes QCRI's machine translation systems for the IWSLT 2016 evaluation campaign, focusing on Arabic-English and English-Arabic tracks. They built both Phrase-based and Neural machine translation models. A Neural MT system, trained by stacking data from different genres through fine-tuning, and applying ensemble over 8 models, outperformed a strong phrase-based system by 2 BLEU points in the Arabic->English direction. Why it matters: The research highlights the early promise of neural machine translation for Arabic language pairs, demonstrating its potential to surpass traditional methods.
KAUST Discovery Professor Aranda's team has been researching coral adaptation to temperature and ocean acidification. The research is focused on the transgenerational aspect of this adaptation using controlled environments. The research has been ongoing for the past two years. Why it matters: Understanding the epigenetic mechanisms of climate resilience in corals is crucial for conservation efforts in the Red Sea and beyond.
This paper describes the QCRI-Columbia-NYUAD group's Egyptian Arabic-to-English statistical machine translation system submitted to the NIST OpenMT'2015 competition. The system used tools like 3arrib and MADAMIRA for processing and standardizing informal dialectal Arabic. The system was trained using phrase-based SMT with features such as operation sequence model, class-based language model and neural network joint model. Why it matters: The work demonstrates advances in machine translation for dialectal Arabic, a challenging but important area for regional communication and NLP research.
KAUST · · Research Healthcare
KAUST researchers are studying the chemical signals in pearl millet that trigger the germination of Striga seeds, a parasitic plant. The research aims to understand the biological compounds involved in Striga infestation. The goal is to induce Striga germination without host plants, reducing Striga seed banks in infested soils. Why it matters: Addressing Striga infestation can improve crop yields and food security, especially in regions relying on pearl millet.
A study analyzes spam content on trending hashtags on Saudi Twitter, finding that approximately 75% of the total generated content is spam. The paper assesses the performance of previous spam detection systems on a newly gathered dataset and proposes an updated manual classification algorithm to improve accuracy. Adapted features are used to build a new data-driven detection system to respond to spammers' evolving techniques. Why it matters: The high prevalence of spam in Arabic content on Twitter necessitates the development of adaptive detection techniques to maintain the quality and trustworthiness of online information in the region.