Pith. sign in

REVIEW 22 cited by

AraBERT: Transformer-based Model for Arabic Language Understanding

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2003.00104 v4 pith:UVBHJJSK submitted 2020-02-28 cs.CL

Wissam Antoun , Fady Baly , Hazem Hajj This is my paper · ORCID
classification cs.CL
keywords languagearabicarabertbertmodelsstate-of-the-arttasksvery
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The Arabic language is a morphologically rich language with relatively few resources and a less explored syntax compared to English. Given these limitations, Arabic Natural Language Processing (NLP) tasks like Sentiment Analysis (SA), Named Entity Recognition (NER), and Question Answering (QA), have proven to be very challenging to tackle. Recently, with the surge of transformers based models, language-specific BERT based models have proven to be very efficient at language understanding, provided they are pre-trained on a very large corpus. Such models were able to set new standards and achieve state-of-the-art results for most NLP tasks. In this paper, we pre-trained BERT specifically for the Arabic language in the pursuit of achieving the same success that BERT did for the English language. The performance of AraBERT is compared to multilingual BERT from Google and other state-of-the-art approaches. The results showed that the newly developed AraBERT achieved state-of-the-art performance on most tested Arabic NLP tasks. The pretrained araBERT models are publicly available on https://github.com/aub-mind/arabert hoping to encourage research and applications for Arabic NLP.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 22 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 619 citations worldwide. Full citation record

  1. Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs

    cs.CL 2025-05 conditional novelty 6.0 of 10

    The new Fann or Flop benchmark measures LLM comprehension of Arabic poetry through expert-written verse explanations and shows current LLMs perform poorly on interpretive depth.

  2. EmoHopeSpeech: An Annotated Dataset of Emotions and Hope Speech in English and Arabic

    cs.CL 2025-05 reject novelty 6.0 of 10

    EmoHopeSpeech is a proposed Arabic-English emotion and hope speech corpus whose claimed reliability is contradicted by its own tables.

  3. Reducing Traffic Wastage in Video Streaming via Bandwidth-Efficient Bitrate Adaptation

    cs.NI 2024-12 conditional novelty 6.0 of 10

    BE-ABR reduces video streaming traffic wastage by about 60 percent by actively controlling buffered data volume through planned waits and a Transformer-based delay predictor, while keeping viewing quality about the same.

  4. Linking Hadith Narrator Identities Across Heterogeneous Arabic Biographical Databases: A Multi-Signal Entity Resolution Pipeline

    cs.DL 2026-06 conditional novelty 5.5 of 10

    A name-only then multi-signal entity-resolution pipeline links Sanadset narrators to Hawramani and Muslimscholars, releasing 94k+95k stratified links and a 185k-node transmission graph.

  5. Evaluation of Adversarial Robustness in Arabic Language Models

    cs.CL 2026-07 conditional novelty 5.0 of 10

    Arabic BERT-family sentiment models lose up to 92% accuracy under diacritics and 58% under conjunction attacks; paraphrase attacks cut accuracy by 76% on average, and adversarial training only partially helps.

  6. A Signer-Invariant Conformer and Multi-Scale Fusion Transformer for Continuous Sign Language Recognition

    cs.CV 2025-08 conditional novelty 5.0 of 10

    The paper reports state-of-the-art WERs of 13.07% (signer-independent) and 47.78% (unseen sentences) on Isharah-1000 using a conformer and a multi-scale fusion transformer.

  7. Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Components

    cs.IR 2025-06 conditional novelty 5.0 of 10

    For Arabic retrieval-augmented generation, sentence-aware chunking, BGE-M3 and Multilingual-E5-large embeddings, bge-reranker-v2-m3, and Aya-8B yield the highest RAGAS scores across six Arabic datasets.

  8. Kuwain 1.5B: An Arabic SLM via Language Injection

    cs.CL 2025-04 conditional novelty 5.0 of 10

    Kuwain 1.5B, built by freezing TinyLlama's original layers and training eight added layers plus a 26K Arabic tokenizer, improves Arabic benchmark average from 36.95 to 44.49 while keeping English near 53.28.

  9. A Novel Dialect-Aware Framework for the Classification of Arabic Dialects and Emotions

    cs.CL 2025-02 reject novelty 5.0 of 10

    A framework using embeddings, clustering, and a fine-tuned Arabic BERT claims improved Arabic dialect classification and automatic generation of dialect-aware emotion lexicons.

  10. MultiProSE: A Multi-label Arabic Dataset for Propaganda, Sentiment, and Emotion Detection

    cs.CL 2025-02 conditional novelty 5.0 of 10

    MultiProSE adds manual sentiment and emotion labels to the 8,000-paragraph Arabic ArPro propaganda corpus and reports BERT and GPT-4o-mini baselines.

  11. AIN: The Arabic INclusive Large Multimodal Model

    cs.CV 2025-01 conditional novelty 5.0 of 10

    AIN, a 7B-parameter Arabic English multimodal model fine-tuned from Qwen2-VL on 3.6M samples, reports state-of-the-art Arabic scores including a 3.4-point average gain over GPT-4o on CAMEL-Bench.

  12. CVPD at QIAS 2025 Shared Task: An Efficient Encoder-Based Approach for Islamic Inheritance Reasoning

    cs.CL 2025-08 conditional novelty 4.0 of 10

    An encoder-based relevance-scoring system achieves 69.87% accuracy on Islamic inheritance multiple-choice questions, below Gemini's 87.60% but with far smaller compute.

  13. Enhanced Arabic Text Retrieval with Attentive Relevance Scoring

    cs.CL 2025-07 conditional novelty 4.0 of 10

    An Arabic dense retriever using a trainable attentive scoring module instead of dot-product similarity reports improved top-k passage retrieval on ArabicaQA.

  14. The Role of Orthographic Consistency in Multilingual Embedding Models for Text Classification in Arabic-Script Languages

    cs.CL 2025-07 reject novelty 4.0 of 10

    Language-specific RoBERTa models for four Arabic-script languages beat multilingual baselines on news classification, though the claimed orthographic-consistency mechanism is not demonstrated.

  15. Multi-task Learning with Active Learning for Arabic Offensive Speech Detection

    cs.CL 2025-06 conditional novelty 4.0 of 10

    A multi-task Arabic offensive speech detector with entropy-based active learning and weighted emoji tokens reports 85.42% macro F1 on OSACT2022 using roughly 3,300 training samples.

  16. GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Training

    cs.CL 2025-05 reject novelty 4.0 of 10

    GATE's Arabic-Triplet-Matryoshka-V2 reports the highest average scores on the MTEB Arabic STS17/STS22/STS22-v2 tasks among the models compared in the paper.

  17. Comparative Approaches to Sentiment Analysis Using Datasets in Major European and Arabic Languages

    cs.CL 2025-01 reject novelty 4.0 of 10

    A comparative fine-tuning study reports that XLM-R beats BERT and mBERT in Finnish and Italian sentiment classification, but the claimed advantage for morphologically complex languages is contradicted by the Hungarian...

  18. Optimized Quran Passage Retrieval Using an Expanded QA Dataset and Fine-Tuned Language Models

    cs.CL 2024-12 reject novelty 4.0 of 10

    Fine-tuning Arabic BERT variants on an expanded, rephrased Qur'an QA dataset improves passage retrieval scores, with AraBERT-base reaching MAP@10 0.36 and MRR 0.59.

  19. DS@GT ARC at CheckThat! 2026: LLM-Based Trace Ranking and Grouped Reward Modeling for Multilingual Numerical Claim Verification

    cs.CL 2026-07 conditional novelty 3.5 of 10

    LoRA-tuned LLM trace scoring beats a TF-IDF grouped reward model on most English metrics and Recall@5, AraBERT beats multilingual BERT on Arabic, and prompt-based sub-claim decomposition hurts rather than helps.

  20. LLM-SEM: A Sentiment-Based Student Engagement Metric Using LLMS for E-Learning Platforms

    cs.CL 2024-12 reject novelty 3.0 of 10

    LLM-SEM scores e-learning engagement by adding normalized views, likes, and an LLM-derived sentiment polarity, but offers no validation that the score measures engagement.

  21. Can bidirectional encoder become the ultimate winner for downstream applications of foundation models?

    cs.CL 2024-11 unverdicted novelty 1.0 of 10

    A review of bidirectional encoder models (BERT and variants) and their performance on GLUE and SQuAD relative to one-way generative models.

  22. Large Language Models and Arabic Content: A Review

    cs.CL 2025-05 reject

    A survey of Arabic LLMs and Arabic NLP tasks that reports no new experiments, results, or datasets.

Pith tools