Related papers: CALText: Contextual Attention Localization for Off…

Cross-lingual speech emotion recognition is an important task for practical applications. The performance of automatic speech emotion recognition systems degrades in cross-corpus scenarios, particularly in scenarios involving multiple…

Zero-shot ASR for Arabic remains challenging: while multilingual models perform well on Modern Standard Arabic (MSA), error rates rise sharply on dialectal and accented speech due to linguistic mismatch and scarce labeled data. We study…

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…

Code Language Models (CodeLLMs) traditionally learn attention based solely on statistical input-output token correlations ("machine attention"). In contrast, human developers rely on intuition, selectively fixating on semantically salient…

Converting images of Arabic text into plain text is a widely researched topic in academia and industry. However, recognition of Arabic handwritten and printed text presents difficult challenges due to the complex nature of variations of the…

In multi-turn dialogue generation, response is usually related with only a few contexts. Therefore, an ideal model should be able to detect these relevant contexts and produce a suitable response accordingly. However, the widely used…

Large language models (LLMs) often exhibit Context Faithfulness Hallucinations, where outputs deviate from retrieved information due to incomplete context integration. Our analysis reveals a strong correlation between token-level…

Urdu is a widely spoken language in South Asia. Though immoderate literature exists for the Urdu language still the data isn't enough to naturally process the language by NLP techniques. Very efficient language models exist for the English…

Handwritten mathematical expression recognition (HMER) is challenging in image-to-text tasks due to the complex layouts of mathematical expressions and suffers from problems including over-parsing and under-parsing. To solve these, previous…

In this work, we focus on the problem of grounding language by training an agent to follow a set of natural language instructions and navigate to a target object in an environment. The agent receives visual information through raw pixels…

In real-world applications, Large Language Models (LLMs) often hallucinate, even in Retrieval-Augmented Generation (RAG) settings, which poses a significant challenge to their deployment. In this paper, we introduce AggTruth, a method for…

Recently, attention based models have been used extensively in many sequence-to-sequence learning systems. Especially for image captioning, the attention based models are expected to ground correct image regions with proper generated words.…

In natural language processing, multilingual models like mBERT and XLM-RoBERTa promise broad coverage but often struggle with languages that share a script yet differ in orthographic norms and cultural context. This issue is especially…

Encoder-decoder models have become an effective approach for sequence learning tasks like machine translation, image captioning and speech recognition, but have yet to show competitive results for handwritten text recognition. To this end,…

Multilingual Large Language Models (LLMs) often provide suboptimal performance on low-resource languages like Urdu. This paper introduces UrduLLaMA 1.0, a model derived from the open-source Llama-3.1-8B-Instruct architecture and continually…

The standard content-based attention mechanism typically used in sequence-to-sequence models is computationally expensive as it requires the comparison of large encoder and decoder states at each time step. In this work, we propose an…

Language models (LMs) often struggle to pay enough attention to the input context, and generate texts that are unfaithful or contain hallucinations. To mitigate this issue, we present context-aware decoding (CAD), which follows a…

The cursive nature of multilingual characters segmentation and recognition of Arabic, Persian, Urdu languages have attracted researchers from academia and industry. However, despite several decades of research, still multilingual characters…

Handwritten character recognition is an active area of research with applications in numerous fields. Past and recent works in this field have concentrated on various languages. Arabic is one language where the scope of research is still…

Automatic identification of script is an essential component of a multilingual OCR engine. In this paper, we present an efficient, lightweight, real-time and on-device spatial attention based CNN-LSTM network for scene text script…