Related papers: Restoring Hebrew Diacritics Without a Dictionary

We present a novel approach to lexical error recovery on textual input. An advanced robust tokenizer has been implemented that can not only correct spelling mistakes, but also recover from segmentation errors. Apart from the orthographic…

We present a semantic role labeling resource for Hebrew built semi-automatically through annotation projection from English. This corpus is derived from the multilingual OpenSubtitles dataset and includes short informal sentences, for which…

Using large language models (LLMs) to generate source code from natural language prompts is a popular and promising idea with a wide range of applications. One of its limitations is that the generated code can be faulty at times, often in a…

This study focuses on the design of multiple Arabic diacritical marks and to developing a model that generates the stacking of multiples Arabic diacritics in order to integrate it into a system of Arabic composition. The problem concerns…

There are more than 80,000 character categories in Chinese while most of them are rarely used. To build a high performance handwritten Chinese character recognition (HCCR) system supporting the full character set with a traditional…

We explore the capabilities of LVLMs and LLMs in deciphering rare scripts not encoded in Unicode. We introduce a novel approach to construct a multimodal dataset of linguistic puzzles involving such scripts, utilizing a tokenization method…

Publicly available, large pretrained LanguageModels (LMs) generate text with remarkable quality, but only sequentially from left to right. As a result, they are not immediately applicable to generation tasks that break the unidirectional…

Modern large language models often encode sensitive, harmful, or copyrighted knowledge, raising the need for post-hoc unlearning-the ability to remove specific domains of knowledge from a model without full retraining. A major bottleneck in…

We introduce MILE-RefHumEval, a reference-free framework for evaluating Large Language Models (LLMs) without ground-truth annotations or evaluator coordination. It leverages an ensemble of independently prompted evaluators guided by a…

Hieroglyphs, as logographic writing systems, encode rich semantic and cultural information within their internal structural composition. Yet, current advanced Large Language Models (LLMs) and Multimodal LLMs (MLLMs) usually remain…

Offline handwritten text line recognition is a hard task that requires both an efficient optical character recognizer and language model. Handwriting recognition state of the art methods are based on Long Short Term Memory (LSTM) recurrent…

Arabic Optical Character Recognition (OCR) and Handwriting Recognition (HWR) pose unique challenges due to the cursive and context-sensitive nature of the Arabic script. This study introduces Qalam, a novel foundation model designed for…

This article presents and validates an ideal, four-stage workflow for the high-accuracy transcription and analysis of challenging medieval legal documents. The process begins with a specialized Handwritten Text Recognition (HTR) model,…

The Hadamard Layer, a simple and computationally efficient way to improve results in semantic segmentation tasks, is presented. This layer has no free parameters that require to be trained. Therefore it does not increase the number of model…

Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with different layers…

Chemputation is the process of programming chemical robots to do experiments using a universal symbolic language, but the literature can be error prone and hard to read due to ambiguities. Large Language Models (LLMs) have demonstrated…

Arabic text recognition is a challenging task because of the cursive nature of Arabic writing system, its joint writing scheme, the large number of ligatures and many other challenges. Deep Learning DL models achieved significant progress…

We present Knesset-DictaBERT, a large Hebrew language model fine-tuned on the Knesset Corpus, which comprises Israeli parliamentary proceedings. The model is based on the DictaBERT architecture and demonstrates significant improvements in…

The high inference cost of Large Language Models (LLMs) poses challenges, especially for tasks requiring lengthy outputs. However, natural language often contains redundancy, which presents an opportunity for optimization. We have observed…

Diffusion models have achieved remarkable progress across various visual generation tasks. However, their performance significantly declines when generating content at resolutions higher than those used during training. Although numerous…