TURJUMAN: A Public Toolkit for Neural Arabic Machine Translation
Not on the map. Why?
Abstract (arXiv)
We present TURJUMAN, a neural toolkit for translating from 20 languages into Modern Standard Arabic (MSA). TURJUMAN exploits the recently-introduced text-to-text Transformer AraT5 model, endowing it with a powerful ability to decode into Arabic. The toolkit offers the possibility of employing a number of diverse decoding methods, making it suited for acquiring paraphrases for the MSA translations as an added value. To train TURJUMAN, we sample from publicly available parallel data employing a simple semantic similarity method to ensure data quality. This allows us to prepare and release AraOPUS-20, a new machine translation benchmark. We publicly release our translation toolkit (TURJUMAN) as well as our benchmark dataset (AraOPUS-20).
Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 22 of its 59 references that are in the map. First posted on arXiv 27 May 2022.
Builds on
22 of 59 references.
References · 22
- 2017Attention Is All You Needcited by 60,361
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
- 2019The Curious Case of Neural Text Degenerationcited by 2,916
- 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
- 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
- 2018Hierarchical Neural Story Generationcited by 1,193
- 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
- 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 593
- 2021Datasets: A Community Library for Natural Language Processingcited by 530
10 more
- 2019MASS: Masked Sequence to Sequence Pre-training for Language Generationcited by 347
- 2017Data Augmentation for Low-Resource Neural Machine Translationcited by 139
- 2018Phrase-Based & Neural Unsupervised Machine Translationcited by 138
- 2021AraT5: Text-to-Text Transformers for Arabic Language Generationcited by 63
- 2019AraNet: A Deep Learning Toolkit for Arabic Social Mediacited by 14
- 2021Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translationcited by 10
- 2017QCRI Machine Translation Systems for IWSLT 16cited by 3
- 2016First Result on Arabic Neural Machine Translationcited by 2
- 2018A Recipe for Arabic-English Neural Machine Translationcited by 2
- 2019Simple Automatic Post-editing for Arabic-Japanese Machine Translationcited by 2
Built on by
Citing papers per year: 2023: 4; 2024: 3; 2025: 3; 2026: 2.
12 papers.
- 2023Dolphin: A Challenging and Diverse Benchmark for Arabic NLGcited by 22
- 2023TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varietiescited by 16
- 2024Toucan: Many-to-Many Translation for 150 African Language Pairscited by 8
- 2023Octopus: A Multitask Model and Toolkit for Arabic Natural Language Generationcited by 6
- 2025Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Modelcited by 2
- 2023An Evaluation of Persian-English Machine Translation Datasets with Transformerscited by 1
- 2024DarijaBanking: A New Resource for Overcoming Language Barriers in Banking Intent Detection for Moroccan Arabic Speakerscited by 1
- 2025Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?cited by 1
- 2026Alexandria: A Multi-Domain Dialectal Arabic Machine Translation Dataset for Culturally Inclusive and Linguistically Diverse LLMscited by 1
- 2026AlexandriaX 2026: The First Shared Task on Dialectal Arabic Machine Translationcited by 1
- 2024SinaTools: Open Source Toolkit for Arabic Natural Language Processingcited by 0
- 2025MASRAD: Arabic Terminology Management Corpora with Semi-Automatic Constructioncited by 0
- 2026AlexandriaX 2026: The First Shared Task on Dialectal Arabic Machine Translation19 Sep 2026
- 2026Alexandria: A Multi-Domain Dialectal Arabic Machine Translation Dataset for Culturally Inclusive and Linguistically Diverse LLMs19 Jan 2026
- 2025Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?27 Jul 2025
- 2025Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model23 May 2025
- 2025MASRAD: Arabic Terminology Management Corpora with Semi-Automatic Construction24 Mar 2025
- 2024SinaTools: Open Source Toolkit for Arabic Natural Language Processing3 Nov 2024
- 2024Toucan: Many-to-Many Translation for 150 African Language Pairs5 Jul 2024
- 2024DarijaBanking: A New Resource for Overcoming Language Barriers in Banking Intent Detection for Moroccan Arabic Speakers26 May 2024
- 2023Octopus: A Multitask Model and Toolkit for Arabic Natural Language Generation24 Oct 2023
- 2023TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varieties6 Aug 2023
- 2023Dolphin: A Challenging and Diverse Benchmark for Arabic NLG24 May 2023
- 2023An Evaluation of Persian-English Machine Translation Datasets with Transformers1 Feb 2023