arXiv:2608. 02609v1 Announce Type: cross Abstract: Half a million cuneiform clay tablets survive in museums worldwide, yet modern users can neither read nor write in the world's oldest writing system, leaving a 4,000-year cultural barrier that existing NLP tools have only partially addressed.
UNESCO considers the Assyrian (Syriac) language an endangered language. Although Assyrians speak the language worldwide, the speaking population is uncertain (ranging from 500,000 to 1,500,000). Syria...
arXiv:2609.18529v1 Announce Type: new Abstract: UNESCO considers the Assyrian (Syriac) language an endangered language. Although Assyrians speak the language worldwide, the speaking population is unc...
arXiv:2608.30092v1 Announce Type: cross Abstract: We present Arkios, a 1.04B-parameter dense transformer pretrained from scratch on 150B tokens of bilingual English-Nepali text, using a custom single...
PyPottery is an open‑source, AI‑powered suite that semi‑automates the entire ceramic documentation pipeline, comprising four modules: PyPotteryScan for image extraction and handwriting recognition, PyPotteryInk for automatic inking of pencil drawings, PyPotteryTrace for semantically‑aware vectorization, and PyPotteryLayout for automated layout generation. In a study of 50 hand‑drawn sheets with 240 pottery drawings from the Terramara di Montale in Italy, users reported a median perceived speedup of 40× compared to traditional workflows, with a range from 17.5× to 120×. The results demonstrate significant time savings and suggest that AI can shift cognitive labor toward augmentation rather than full automation.
Learning to read cuneiform tablets is an extremely demanding task; consequently, of the roughly half million excavated tablets, only a small fraction has been analysed by Assyriologists. Computer vision offers a promising avenue for decipherment but requires large, densely annotated datasets.
Ancient-Bench is a new benchmark for recognizing text on ancient Chinese artifacts, comprising 2,700 images that span 3,000 years of character evolution, nine artifact categories, and seven historical script forms. It introduces three annotation standards—symbol, character, and parsing standardization—to accommodate medium‑specific characteristics and enable consistent evaluation. Experiments show that current Vision‑Language Models and OCR specialists still struggle with variant characters, specialized symbols, and hallucination, indicating the task remains largely unsolved.
arXiv:2608. 07629v1 Announce Type: cross Abstract: Multilingual neural machine translation models such as NLLB-200 cover 200 languages but leave thousands unsupported, including most Grassfields Bantu languages of Cameroon.
SDUs DAISY is a factual knowledge benchmark focused on Danish cultural heritage, drawing topics from the Danish Culture Canon 2006. The dataset contains 741 manually verified closed‑ended question‑answer pairs generated by querying Wikipedia pages for each canon artifact, covering a wide historical span from 1300 BCE to contemporary pop music, design, and architecture. Baseline tests with state‑of‑the‑art language models show very low performance (best BLEU 0.17, F1 0.27), highlighting the benchmark’s difficulty and the need for improved cultural knowledge in AI systems.
arXiv:2608.28635v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have advanced document understanding, visual question answering, and text extraction. However, their...
The paper introduces SCAM, a line-level dataset of digitized Sahidic Coptic ancient manuscripts designed for Handwritten Text Recognition in low-resource settings. SCAM captures realistic challenges such as varied acquisition conditions, ink fading, bleed-through, and material deterioration, while also presenting linguistic difficulties due to the scarce resources, uncommon alphabet, and dialect-specific diacritics of Sahidic Coptic. The authors benchmark several state‑of‑the‑art HTR methods, demonstrating the performance gap between modern, well‑resourced scripts and historically grounded, low‑resource scenarios.
The paper "When Explanations Cannot Be Read: Measuring and Correcting SHAP and LIME Rendering for Right-to-Left Languages" identifies that standard SHAP and LIME visualizations, designed for left‑to‑right scripts, fail to display attribution values correctly for right‑to‑left languages such as Urdu, Arabic, Persian, and Hebrew. It introduces SHAP‑RTL, a rendering layer that preserves the original attribution values while correcting reading direction, script shaping, and font selection for each language. The authors evaluate SHAP‑RTL on hate‑and‑offensive‑language datasets using TF‑IDF and logistic regression, showing that default rendering yields high character error rates, while SHAP‑RTL maintains correct visualizations across all tested languages.
arXiv:2606.26040v2 Announce Type: replace Abstract: AI translation of literary works is increasingly common. While the content may be rendered adequately, we do not know enough about how readers expe...