Sign inSubmit
Tips: “quotes” for a phrase · author:Lee · a DOI goes straight to its article

23 results for “Fine-Tuning”
Set a search alert
Research ArticleOpen accessPhrase in the titleFew-shot Fine-tuning of BERT Multilingual for Hindi Word Sense DisambiguationShailendra Kumar Patel, Rakesh Kumar, Anuj Kumar SirohiWord Sense Disambiguation (WSD) is a fundamental task in Natural Language Processing (NLP), addressing the challenge of identifying correct word meanings in context. This task is particularly complex for morphologically rich and resource-limited languages like Hindi, which exhibit significant lexical ambiguity compounded by limited availability of annotated corpora. To address these challenges, we propose a supervised approach combining the multilingual … …Journal of Computer Science, Vol. 21, Issue 11 · 26 Dec 2025 · 2,250 accessesView PDFCite
Research ArticleOpen accessEvery word in the titleEmpowering Small Language Models With Chain of Thought and Parameter Efficient Fine Tuning for Efficient Deep ReasoningAryan Raina, Shiwani Gupta, Jagruti Jadhav et al.Small Language Models (SLMs) run faster and fit on modest hardware, yet solving multi-step logic problems has traditionally been difficult for them. This work investigates a systematic, multi-model framework that combines Chain-of-Thought (CoT) prompting with Low-Rank Adaptation (LoRA) parameter-efficient fine-tuning, and measures the contribution of each component independently. We evaluate three SLMs (TinyLlama-1.1B, Phi-3-mini-4k-instruct, and Qwen2.5-1.5B) using 1,164 training samples … …Journal of Computer Science, Vol. 22, Issue 8 · 8 Sep 2026 · 862 accessesView PDFCite
Research ArticleOpen accessEvery word in the titleDiscovery of Evolutionary Divergence of Biological Nitrogen Fixation and Photosynthesis: Fine Tuning of Biogenesis of the NifH and the ChlL by a Peptidyl-Prolyl Cis/Trans IsomeraseNara Gavini, Sinny Delacroix, Kelvin Harris Jr., Lakshmi PulakatProblem statement: Despite the structural and functional similarities between the nitrogenase that performs biological nitrogen fixation reaction and the Dark Protochlorphyllide Oxidoreductase (DPOR) that performs chlorophyll-biosynthesis, attempts to substitute nitrogenase-components with DPOR-components have hitherto failed. This investigation was undertaken to test if Chlamydomonas reinhardtii protochlorophyllide (Pchlide) reductase (ChlL) that shares some structural similarity with Nitrogenase Reductase (NifH) could complement the … …American Journal of Biochemistry and Biotechnology, Vol. 7, Issue 4 · 17 Feb 2012 · 7,614 accessesView PDFCite
Research ArticleOpen accessIn the keywordsSuicide Ideation and Risk Detection from Social Media Using GPT ModelsSara Lasri, El Habib Nfaoui, Karima MrizikAs a reason for the sensitiveness of suicide ideation and its considerable impact on people's lives, the demand to treat and prevent the suicide ideation issue has become an obligation. Suicide ideation is a result of a combination of psychological pain and hopelessness. According to the World Health Organization, the task of reducing the global suicide mortality rate is a … …Journal of Computer Science, Vol. 20, Issue 10 · 26 Aug 2024 · 5,704 accessesView PDFCite
Research ArticleOpen accessIn the keywordsImplementation of Single Candidate Loss Optimization Algorithm for Loss Optimization of Bhojpuri-English Machine Translation ModelRituraj Dixit, Sarabjeet Singh Bedi, Ibrahim Aljubayri, Mohammad Zubair KhanMachine translation of low-resource Indian languages is necessary as most of the regions still know and speak their specific dialects and are still not comfortable understanding the English language. Indian languages are morphologically rich, due to which there are two big challenges, Ambiguity and Domain adaption, which are faced by researchers during the translation. Lack of data also increases the … …Journal of Computer Science, Vol. 21, Issue 5 · 17 Apr 2025 · 5,151 accessesView PDFCite
Research ArticleOpen accessIn the abstractAbstractive Summarization of Long Educational Transcripts in the Era of GenAIDeepa Fernandes, Rupali Sunil WaghThe surge in online video data presents the imperative requirement of summarizing it for information compression, efficient understanding, and to support decision-making. Recent research studies have predominantly utilized structured input data for summarization. This paper explores the current state-of-the-art models in summarizing unstructured, conversational, and long transcript data. We further apply a transfer learning approach using a fine-tuned BART model, … …Journal of Computer Science, Vol. 22, Issue 8 · 7 Sep 2026 · 403 accessesView PDFCite
Research ArticleOpen accessIn the abstractSelf-Supervised Contrastive Learning for Steering Angle Prediction in Autonomous Driving SimulationsMaxson Phang, Suryadiputra LiawatimenaPredicting steering angles is a crucial task in autonomous driving, with end-to-end deep learning being a widely used approach. However, such models often suffer from overfitting to learned trajectories, limiting their generalization to new data. To address this, self-supervised contrastive learning is explored as an alternative, allowing models to learn meaningful representations without labeled data. The primary objective is to … …Journal of Computer Science, Vol. 21, Issue 9 · 20 Oct 2025 · 2,581 accessesView PDFCite
Research ArticleOpen accessIn the abstractPleural Effusion Detection Using Optimized Pretrained ModelsRehab Fathi Ibrahim, Nashwa Mohamed Elsayed et al.Pleural effusion is an abnormal accumulation of fluid in the pleural cavity, posing a significant thoracic issue with various causes. Even with a variety of diagnostic techniques, accurate diagnosis remains challenging. Delays in diagnosis and treatment heighten the risks of the disease. In this paper, we introduce a novel approach by leveraging the Grey Wolf Optimizer (GWO) to systematically optimize … …Journal of Computer Science, Vol. 21, Issue 8 · 17 Oct 2025 · 2,308 accessesView PDFCite
Research ArticleOpen accessIn the abstractImprovement of Moroccan Dialect Sentiment Analysis Using Arabic BERT-Based ModelsGhizlane Bourahouat, Manar Abourezq, Najima DaoudiThis study addresses the crucial task of sentiment analysis in natural language processing, with a particular focus on Arabic, especially dialectal Arabic, which has been relatively understudied due to inherent challenges. Our approach centers on sentiment analysis in Moroccan Arabic, leveraging BERT models that are pre-trained in the Arabic language, namely AraBERT, QARIB, ALBERT, AraELECTRA, and CAMeLBERT. These models are … …Journal of Computer Science, Vol. 20, Issue 2 · 27 Dec 2023 · 6,545 accessesView PDFCite
Research ArticleOpen accessIn the abstractMeasurement of Cooling Load-Based Occupant Behavior in Under-Actuated Zones: A Time-Variance ApproachYaddarabullah, Yusuf Maulana Akbar, Aedah Binti Abd Rahman, Amna SaadThis research is dedicated to the enhancement of Heating, Ventilation, and Air-Conditioning (HVAC) systems through an innovative investigation of occupant behavior within under-actuated zones. These zones are strategically positioned to elevate indoor air quality and comfort through the intelligent utilization of HVAC systems. However, accurately measuring the cooling loads within these zones, which are inherently influenced by the presence of … …American Journal of Applied Sciences, Vol. 20, Issue 1 · 11 Dec 2023 · 6,158 accessesView PDFCite