Cross-Language Learning within Arabic Script for Low-Resource HTR

• URL: http://arxiv.org/abs/2605.02089v1
• Date: Sun, 03 May 2026 23:18:21 GMT
• Title: Cross-Language Learning within Arabic Script for Low-Resource HTR
• Abstract summary: Cross-script recognition is largely driven by script-level overlap rather than uniform accuracy improvements.<n>We conduct a controlled line-level study of cross-script joint training for Arabic-script HTR under low-resource regimes.<n>On Persian (PHTD), joint training achieves a Character Error Rate (CER) of 9.99, surpassing previously reported results.
• Score: 5.227985502946548
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Handwritten Text Recognition (HTR) under limited labeled data remains a challenging problem, particularly for Arabic-script languages. Although modern sequence-based recognizers perform well in high-resource settings, their accuracy degrades sharply as training data becomes scarce. Arabic-script languages share a common writing system with substantial character overlap, motivating cross-script training as a strategy to mitigate data scarcity. We performed experiments on Arabic, Urdu, and Persian scripts and achieved improvements over single-script baselines (new SotA especially for low-resource settings). A key finding of our experiments is that cross-script transfer is largely driven by script-level overlap rather than uniform accuracy improvements. Through a statistical character-level analysis we show that gains are structurally concentrated on characters shared across scripts, while language-specific characters exhibit limited or negative transfer. These findings provide insight into transfer dynamics in low-resource script families. Detailed results include: We conduct a controlled line-level study of cross-script joint training for Arabic-script HTR under low-resource regimes (number of samples K \in 100, 500, 1000 labeled lines) on Arabic (KHATT), Urdu (NUST-UHWR), and Persian (PHTD). A CRNN model is trained on the union of multiple related Arabic-script datasets and evaluated on individual target languages. On Persian (PHTD), joint training achieves a Character Error Rate (CER) of 9.99, surpassing previously reported results despite not using the full available training data. On an Urdu dataset (UNHD), joint training reduces CER from 17.20 to 14.45. Code and data splits are released to ensure reproducibility.1

Related papers

• Performance Gap Analysis between Latin and Arabic Scripts HTR [5.227985502946548]
  We present a comprehensive study of Arabic and Latin scripts HTR using a unified CRNN model for line-level HTR.<n>Our results show the performance gap remains: it is large in low-resource settings, decreases with more data, but remains even at full scale, with a consistent difference of 5-7 CER points.
  arXiv  Detail & Related papers  (2026-06-17T10:00:22Z)
• The Role of Orthographic Consistency in Multilingual Embedding Models for Text Classification in Arabic-Script Languages [30.39307182175106]
  We introduce the Arabic Script RoBERTa (AS-RoBERTa) family: four RoBERTa-based models, each pre-trained on a large corpus tailored to its specific language.<n>Our results highlight the value of script-aware specialization for languages using the Arabic script and support further work on pre-training strategies rooted in script and language specificity.
  arXiv  Detail & Related papers  (2025-07-24T19:28:33Z)
• Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation [36.92567530333872]
  We study adding a new language, i.e. Persian, to a large language model (LLMs)<n>We employ a multi-stage approach involving pretraining on monolingual Persian data.<n>We evaluate the model's performance at each stage on generation and classification tasks.
  arXiv  Detail & Related papers  (2024-12-17T23:18:06Z)
• Cross-lingual Contextualized Phrase Retrieval [63.80154430930898]
  We propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval. We train our Cross-lingual Contextualized Phrase Retriever (CCPR) using contrastive learning. On the phrase retrieval task, CCPR surpasses baselines by a significant margin, achieving a top-1 accuracy that is at least 13 points higher.
  arXiv  Detail & Related papers  (2024-03-25T14:46:51Z)
• NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages [54.808217147579036]
  We conduct a case study on Indonesian local languages. We compare the effectiveness of online scraping, human translation, and paragraph writing by native speakers in constructing datasets. Our findings demonstrate that datasets generated through paragraph writing by native speakers exhibit superior quality in terms of lexical diversity and cultural content.
  arXiv  Detail & Related papers  (2023-09-19T14:42:33Z)
• Strategies for improving low resource speech to text translation relying on pre-trained ASR models [59.90106959717875]
  This paper presents techniques and findings for improving the performance of low-resource speech to text translation (ST) We conducted experiments on both simulated and real-low resource setups, on language pairs English - Portuguese, and Tamasheq - French respectively.
  arXiv  Detail & Related papers  (2023-05-31T21:58:07Z)
• MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition [56.408324994409405]
  Multiplexed routing network (MRN) trains a recognizer for each language that is currently seen. MRN effectively reduces the reliance on older data and better fights against catastrophic forgetting. It outperforms existing general-purpose IL methods by large margins.
  arXiv  Detail & Related papers  (2023-05-24T06:03:34Z)
• Ensemble Transfer Learning for Multilingual Coreference Resolution [60.409789753164944]
  A problem that frequently occurs when working with a non-English language is the scarcity of annotated training data. We design a simple but effective ensemble-based framework that combines various transfer learning techniques. We also propose a low-cost TL method that bootstraps coreference resolution models by utilizing Wikipedia anchor texts.
  arXiv  Detail & Related papers  (2023-01-22T18:22:55Z)
• New Results for the Text Recognition of Arabic Maghrib{\=i} Manuscripts -- Managing an Under-resourced Script [0.0]
  We introduce and assess a new modus operandi for HTR models development and fine-tuning dedicated to the Arabic Maghrib=i scripts. The comparison between several state-of-the-art HTR models demonstrates the relevance of a word-based neural approach specialized for Arabic. Results open new perspectives for Arabic scripts processing and more generally for poorly-endowed languages processing.
  arXiv  Detail & Related papers  (2022-11-29T12:21:41Z)
• Graphemic Normalization of the Perso-Arabic Script [47.429213930688086]
  This paper documents the challenges that Perso-Arabic presents beyond the best-documented languages. We focus on the situation in natural language processing (NLP), which is affected by multiple, often neglected, issues. We evaluate the effects of script normalization on eight languages from diverse language families in the Perso-Arabic script diaspora on machine translation and statistical language modeling tasks.
  arXiv  Detail & Related papers  (2022-10-21T21:59:44Z)
• Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts [56.72488923420374]
  Pre-trained language models (LMs) have shown great potential for cross-lingual transfer in low-resource settings. We show the few-shot cross-lingual transfer property of LMs for named recognition (NER) and apply it to solve a low-resource and real-world challenge of code-mixed (Spanish-Catalan) clinical notes de-identification in the stroke.
  arXiv  Detail & Related papers  (2022-04-10T21:46:52Z)
• ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective Feedback [70.5469946314539]
  ChrEnTranslate is an online machine translation demonstration system for translation between English and an endangered language Cherokee. It supports both statistical and neural translation models as well as provides quality estimation to inform users of reliability.
  arXiv  Detail & Related papers  (2021-07-30T17:58:54Z)
• Transliteration of Judeo-Arabic Texts into Arabic Script Using Recurrent Neural Networks [1.933681537640272]
  We train a model to automatically transliterate Judeo-Arabic texts into Arabic script. We employ a recurrent neural network (RNN), combined with the connectionist temporal classification (CTC) loss to deal with unequal input/output lengths. We obtain an improvement over the baseline 9.5% character error, achieving 2% error with our best configuration.
  arXiv  Detail & Related papers  (2020-04-23T18:03:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.