Be aware of overfitting by hyperparameter optimization! by Igor V. Tetko, Ruud van Deursen, Guillaume Godin

“…We also extended the previous analysis by adding a representation learning method based on Natural Language Processing of smiles called Transformer CNN. We show that across all analyzed sets using exactly the same protocol, Transformer CNN provided better results than graph-based methods for 26 out of 28 pairwise comparisons by using only a tiny fraction of time as compared to other methods. …”
Get full text

Extraction-Augmented Generation of Scientific Abstracts Using Knowledge Graphs by Haotong Wang, Yves Lepage

“…Through fine-grained extraction, we reconstructed the Abstract Generation Dataset (AGENDA) and the newly developed ACL Abstract Graph Dataset (ACL-AGD) containing the latest Natural Language Processing (NLP) research, both datasets composed of graph-abstract pairs. …”
Get full text

Improved IEC performance via emotional stimuli-aware captioning by Zibo Zhou, Zhengjun Zhai, Xin Gao, Jiaqi Zhu

“…In this study, we draw inspiration from psychological findings and advances in natural language processing. Specifically, we explore the use of image captions as auxiliary information, combined with visual features, for enhanced emotional discernment. …”
Get full text

Research on the acquisition and identification methods of critical microscopic quality characteristics in the manufacturing process by Zhongyi Wu, Zhenyang Xu, Cheng Liang, Kan Lv, Bin Qin

“…Intelligent acquisition and representation of MQC during machining are realized by using natural language processing (NLP) techniques and topological methods. …”
Get full text

Innovative Mining of User Requirements Through Combined Topic Modeling and Sentiment Analysis: An Automotive Case Study by Yujia Liu, Dong Zhang, Qian Wan, Zhongzhen Lin

“…Driven by advancements in big data, artificial intelligence, and natural language processing, mining user requirements from user-generated content (UGC) on social media has become an effective way to understand these dynamic needs. …”
Get full text

Knowledge Graph as Pre-Training Corpus for Structural Reasoning via Multi-Hop Linearization by Wooyoung Kim, Haemin Jung, Wooju Kim

“…Large language models have demonstrated exceptional performance across various natural language processing tasks. However, their reliance on unstructured text corpora for pre-training limits their effectiveness in tasks requiring structured reasoning such as multi-hop question-answering. …”
Get full text

Aspect-Based Sentiment Analysis for Afaan Oromoo Movie Reviews Using Machine Learning Techniques by Obsa Gelchu Horsa, Kula Kekeba Tune

“…Aspect-based sentiment analysis (ABSA) is the subfield of natural language processing that deals with essentially splitting data into aspects and finally extracting the sentiment polarity as positive, negative, or neutral. …”
Get full text

Electronic medical records as a source of real-world clinical data by A. V. Gusev, B. V. Zingerman, D. S. Tyufilin, V. V. Zinchenko

“…The basis of the proposed methodology is the centralized collection of information from EMR in the so-called data lakes, where as much as possible of raw data on the patient is accumulated and subsequent extraction of data from unstructured records through natural language processing (NLP) models. The proposed technology, subject to continuous improvement, will provide a correct and comprehensive solution for the skilful understanding of any text from any medical record.…”
Get full text

Artificial intelligence-assisted nursing interventions in psychiatry for oral cancer patients: A concise narrative review by Abdulmalik Fareeq Saber, Sirwan Khalid Ahmed, Safin Hussein, Karzan Qurbani

“…AI-driven tools, such as predictive models, natural language processing, and mobile applications, provide novel means of early disease detection, risk assessment, personalized care planning, and real-time patient support. …”
Get full text

Different effects of verbal and visual working memory loads on Language prediction by Shun Liu, Wenpeng Hu, Xiqin Liu

“…This offers novel insights into how verbal WM and visual-spatial WM differentially influence predictive language processing.…”
Get full text

Japanese Short Answer Grading for Japanese Language Learners Using the Contextual Representation of BERT by Dyah Lalita Luhurkinanti, Prima Dewi Purnamasari, Takashi Tsunakawa, Anak Agung Putri Ratna

“…Bidirectional encoder representations from transformer (BERT), which has shown potential for natural language processing (NLP) tasks, is implemented to grade answers without fine-tuning due to the small amount of data. …”
Get full text

Phonological working memory and linguistic processing speed in inferential reading comprehension by Daniela Balonyi Candal, Clara Regina Brandão de Avila

“…Methods To do this, we analyzed information from a database on the assessment of phonological memory (digit span Backward and Forward task), language processing speed (Verbal Fluency and Rapid Automated Naming) and inferential reading comprehension of 66 typical 5th grade students. …”
Get full text

Modelowanie tematyczne w socjologii na przykładzie dobrobytu społecznego: wyzwania metodologiczne i komponent ludzki by Piotr Cichocki, Mariusz Baranowski

“…To empiryczne studium przypadku posłuży także do sformułowania uwag metateoretycznych na temat „kohezji” metod ilościowych i jakościowych w perspektywie uczenia maszynowego (ang. machine learning) i przetwarzania języka naturalnego (ang. natural language processing – NLP).…”
Get full text

Investigating Valency Decreasing Verb Operational Devices: A Case Study of the Oromo Language by Ayub Ismael Jarso, Giorgio Banti

“…This study seeks to contribute to (i) providing a comprehensive analysis of valency-decreasing mechanisms in the Oromo language; (ii) identifying universal patterns or language-specific variations in valency decrease strategies; (iii) informing linguistic theories by examining how operational devices impact verb valency; (iv) offering insights for language documentation, language teaching, and natural language processing (NLP) systems.…”
Get full text

Improving Visual Question Answering by Image Captioning by Xiangjun Shao, Hongsong Dong, Guangsheng Wu

“…Visual Question Answering (VQA) is a challenging task that bridges the computer vision and natural language processing communities. It provide natural language answers to questions related to an associated image. …”
Get full text

Artificial Intelligence in SMEs: Enhancing Business Functions Through Technologies and Applications by Thang Le Dinh, Manh-Chiên Vu, Giang T.C. Tran

“…Through a systematic literature review of 50 studies published between 2016 and 2025, we identify prominent AI technologies, including machine learning, natural language processing, and generative AI, and their applications in enhancing efficiency, decision-making, and innovation across sales and marketing, operations and logistics, finance and other business functions. …”
Get full text

Play, watch, share: the dissemination of the cultural presence of games on video-based social media by Qiaohe Zhang, Yixuan Shao, Xu Li

“…A real-time object detection algorithm from the computer vision (CV) field is used for video emotion detection, and the latent Dirichlet allocation (LDA) approach from the natural language processing (NLP) field is used for text analysis and topic extraction purposes. …”
Get full text

Text intelligent correction in English translation: A study on integrating models with dependency attention mechanism. by Yutong Liu, Shile Zhang

“…Improving translation quality and efficiency is one of the key challenges in the field of Natural Language Processing (NLP). This study proposes an enhanced model based on Bidirectional Encoder Representations from Transformers (BERT), combined with a dependency self-attention mechanism, to automatically detect and correct textual errors in the translation process. …”
Get full text

AI generations: from AI 1.0 to AI 4.0 by Jiahao Wu, Hengxu You, Jing Du

“…AI 1.0 accompanied breakthroughs in pattern recognition and information processing, fueling advances in computer vision, natural language processing, and recommendation systems. AI 2.0 is built on these foundations through real-time decision-making in digital environments, leveraging reinforcement learning and adaptive planning for agentic AI applications. …”
Get full text

Visual Instruction Tuning for Drone Accident Forensics by Arda Surya Editya, Tohari Ahmad, Hudan Studiawan

“…The model's performance was evaluated via the BLEU score, a metric commonly used to assess machine translation and natural language processing models. The results demonstrated that LLaVAFor achieved superior BLEU scores compared with baseline models such as LLaVA, Google Gemini, and ChatGPT. …”
Get full text