Related papers: Analyzing Turkish F and Turkish E keyboard layouts…
We present VBART, the first Turkish sequence-to-sequence Large Language Models (LLMs) pre-trained on a large corpus from scratch. VBART are compact LLMs based on good ideas leveraged from BART and mBART models and come in two sizes, Large…
An F-system is a computational model that performs a folding operation on words of a given language, following directions coded on words of another given language. This paper considers the case in which both given languages are regular, and…
The progressive introduction of the flip teaching (FT) instructional model into higher education has accelerated in recent years. The FT methodology seems to be especially suitable for laboratory practice sessions: before the lab session…
Exploring an efficient and scalable architecture of fault-tolerant quantum computing (FTQC) is vital for demonstrating useful quantum computing. Here, we propose and evaluate a scalable and practical architecture with a…
Federated Learning (FL) is a powerful framework for privacy-preserving distributed learning. It enables multiple clients to collaboratively train a global model without sharing raw data. However, handling noisy labels in FL remains a major…
Measuring the performance of text recognition and text line detection engines is an important step to objectively compare systems and their configuration. There exist well-established measures for both tasks separately. However, there is no…
Few-shot learning is an important, but challenging problem of machine learning aimed at learning from only fewer labeled training examples. It has become an active area of research due to deep learning requiring huge amounts of labeled…
Transformers have achieved state-of-the-art performance in morphological inflection tasks, yet their ability to generalize across languages and morphological rules remains limited. One possible explanation for this behavior can be the…
This work aims to build a multilingual text-to-speech (TTS) synthesis system for ten lower-resourced Turkic languages: Azerbaijani, Bashkir, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Turkmen, Uyghur, and Uzbek. We specifically target the…
The rapid integration of large language models into newsroom workflows has raised urgent questions about the prevalence of AI-generated content in online media. While computational studies have begun to quantify this phenomenon in…
Our study utilizes deep learning methods for the automated transcription of late nineteenth- and early twentieth-century periodicals written in Arabic script Ottoman Turkish (OT) using the Transkribus platform. We discuss the historical…
As the structure of Chinese characters are very different, it is very difficult to input Chinese characters into computer quickly and conveniently. The conventional keyboard does not support the pictorial characters in Chinese language.…
Neural interfaces offer a pathway to intuitive, high-bandwidth interaction, but the sensitive nature of neural data creates significant privacy hurdles for large-scale model training. Federated learning (FL) has emerged as a promising…
A study was undertaken to determine the important usability factors (UF) used in the English and the non-English version of a website. The important usability factors were determined, based on a detailed questionnaire used in an…
We study the problem of designing a state feedback linear quadratic Gaussian (LQG) controller for a system in which the system matrices as well as the process noise covariance are unknown. We do a rigorous comparison between two approaches.…
With the ubiquity of mobile touchscreen devices like smartphones, two widely used text entry methods have emerged: small touch-based keyboards and speech recognition. Although speech recognition has been available on desktop computers for…
Automatic text tagging is an important component in higher level analysis of text corpora, and its output can be used in many natural language processing applications. In languages like Turkish or Finnish, with agglutinative morphology,…
In Turkish, (and possibly in many other languages) verbs often convey several meanings (some totally unrelated) when they are used with subjects, objects, oblique objects, adverbial adjuncts, with certain lexical, morphological, and…
Skill extraction is a critical component of modern recruitment systems, enabling efficient job matching, personalized recommendations, and labor market analysis. Despite T\"urkiye's significant role in the global workforce, Turkish, a…
HeceTokenizer is a syllable-based tokenizer for Turkish that exploits the deterministic six-pattern phonological structure of the language to construct a closed, out-of-vocabulary (OOV)-free vocabulary of approximately 8,000 unique syllable…