Harmonizer: A Universal Signal Tokenization Framework for Multimodal Large Language Models by Amin Amiri, Alireza Ghaffarnia, Nafiseh Ghaffar Nia, Dalei Wu, Yu Liang

“…In summary, Harmonizer integrates natural language processing and signal processing into a coherent tokenization paradigm for efficient, interpretable multimodal learning.…”
Get full text

Synergizing human insight and machine learning: A dual-lens approach to uncovering healthcare research and innovation outcomes by Stijn Horck, Sanne Steens, Jermain Kaminski

“…This study introduces an approach that combines narrative interviews and Natural Language Processing (NLP) to identify patterns associated with innovation project outcomes. …”
Get full text

RAG-Driven Memory Architectures in Conversational LLMs—A Literature Review With Insights Into Emerging Agriculture Data Sharing by Nur Arifin Akbar, Rahool Dembani, Biagio Lenzitti, Domenico Tegolo

“…Despite significant advances in natural language processing, conversational AI systems face persistent challenges in maintaining extensive and contextually coherent dialogues, particularly regarding long-term memory management. …”
Get full text

Analysis of argument structure constructions in a deep recurrent language model by Pegah Ramezani, Pegah Ramezani, Achim Schilling, Achim Schilling, Patrick Krauss, Patrick Krauss

“…In future work, we plan to compare these model-derived representations with neuroimaging data from continuous speech perception, further bridging computational and biological perspectives on language processing.…”
Get full text

Quantitative research on aesthetic value of the world heritage karst based on UGC data: A case study of Huangguoshu Scenic Area. by Xi Zhao, Kangning Xiong, Meng Zhang

“…This article is based on a public perspective, using social media UGC data, crawling images and texts as data sources, and combining SegFormer deep learning models, ArcGIS spatial analysis, natural Language Processing Technology (NLP) and other methods to conduct quantitative research on aesthetic value. …”
Get full text

Periodic insight: Multilingual reputation generation system through daily opinion mining analysis by Achraf Boumhidi, Abdessamad Benlahbib, Erik Cambria, El Habib Nfaoui

“…In the first phase, data preparation, the system incorporates review translation to English, spam filtering, and sarcasm detection to address limitations of language processing and enhance data quality. This prepares the data for the second phase, reputation generation, which utilizes state-of-the-art, aspect-based sentiment analysis techniques, offering a novel approach to calculating reputation by considering specific aspects of products or services. …”
Get full text

Chinese Image Captioning Based on Deep Fusion Feature and Multi-Layer Feature Filtering Block by Xi Yang, Xingguo Jiang, Jinfeng Liu

“…With deep learning achieving remarkable results in computer vision and natural language processing, image captioning has emerged as a key focus area in artificial intelligence research. …”
Get full text

From Theoretical Framework to Empirical Investigation: A Bibliometric Analysis of Research Evolution and Emerging Trends in Polarity Sensitivity Studies Between 1980 and 2023 by Lingda Kong, Yi Li, Yanting Sun, Yong Jiang, Xiaoming Jiang

“…Promising research directions involve the combination of computational modelling, diachronic studies, and applications in language teaching and natural language processing. This study maps the intellectual landscape of polarity sensitivity research while suggesting future directions toward unified theories that address universal and language-specific patterns.…”
Get full text

Evaluating Large Language Models for Preoperative Patient Education in Superior Capsular Reconstruction: Comparative Study of Claude, GPT, and Gemini by Yukang Liu, Hua Li, Jianfeng Ouyang, Zhaowen Xue, Min Wang, Hebei He, Bin Song, Xiaofei Zheng, Wenyi Gan

“… Abstract BackgroundLarge language models (LLMs) are revolutionizing natural language processing, increasingly applied in clinical settings to enhance preoperative patient education. …”
Get full text

InMemQK: A Product Quantization Based MatMul Module for Compute-in-Memory Attention Macro by Pengcheng Feng, Yihao Chen, Jinke Yu, Hao Yue, Zhelong Jiang, Yi Xiao, Wan’ang Xiao, Huaxiang Lu, Gang Chen

“…Large Language Models (LLMs), based on transformer architecture, have demonstrated remarkable capabilities in natural language processing tasks, enabling machines to generate human-like text and engage in meaningful dialogues. …”
Get full text

A method for IoT devices test case generation using language models by Sumit Kumar, Kiran Napte, Ruchi Rani, Sanjeev Kumar Pippal

“…With advancements in Natural Language Processing (NLP) and language models, automated test case generation systems can now create structured test cases in programming languages while ensuring code integrity and style. …”
Get full text

Keyphrase generation for the Russian-language scientific texts using mT5 by Anna V. Glazkova, Dmitry A. Morozov, Marina S. Vorobeva, Andrey Stupnikov

“…The automatic selection of keyphrases is a relevant task of natural language processing since keyphrases help readers find the article easily and facilitate the systematization of scientific texts. …”
Get full text

Privacy-sensitive federated learning for cross-domain adaptation: The Mamba-MoE approach by Muhammad Kashif Jabbar, Huang Jianjun, Ayesha Jabbar, Zaka Ur Rehman

“…Comprehensive evaluations on Natural Language Processing (NLP) and image classification benchmarks demonstrate 91.6% accuracy, 85.4% F1-score, privacy loss ϵ<1.0, computational efficiency of 5 ms/epoch/client, and minimal communication overhead (2 MB/round). …”
Get full text

AI-Powered Platforms for Interactive Nutrition Education Based on WHO (World Health Organization) Guidelines – An Overview by Taiwo Folake Ojo, Oluwaseyi Abiodun Akpor, Yetunde Justinah Talabi, Adeniran Sunday Afolalu

“…Additionally, it investigates how AI improves user engagement through interactive features like gamification, chatbots that employ natural language processing to provide individualized virtual coaching, and dynamic feedback systems for behavior reinforcement and progress monitoring. …”
Get full text

Exploration and Practice of Classification Indexing Combined with Large Language Models by JIANG Peng, REN Yan, ZHU Beiling

“…Large language models (LLMs), with their excellent capabilities in natural language understanding and processing capabilities, have been utilized for various natural language processing tasks such as text generation, automatic summarization, and text classification, which can be integrated into the entire classification process. …”
Get full text

TQAgent: Enhancing Table-Based Question Answering with Knowledge Graphs and Tree-Structured Reasoning by Jianbin Zhao, Pengfei Zhang, Yuzhen Wang, Rui Xin, Xiuyuan Lu, Ripeng Li, Shuai Lyu, Zhonghong Ou, Meina Song

“…Table-based question answering (TableQA) has emerged as an important task in natural language processing, yet existing models face challenges in handling complex reasoning and mitigating hallucinations, especially when dealing with diverse table structures. …”
Get full text

Disorders of Consciousness, Language and Communication Following Severe Brain Injury by Charlène Aubinet, Anaïs Gillet, Amandine Regnier

“…Further research is needed to refine methodologies and better understand the interplay between language processing, communication and levels of consciousness.…”
Get full text

D3: A Small Language Model for Drug-Drug Interaction prediction and comparison with Large Language Models by Ahmed Ibrahim, Abdullah Hosseini, Salma Ibrahim, Aamenah Sattar, Ahmed Serag

“…Large Language Models (LLMs) have significantly advanced Natural Language Processing (NLP) applications, including healthcare. …”
Get full text

The Discursive Strategies in the Spoken Narratives of Multilingual Sepitori and Sesotho Speakers by Ramona Kunene Nicolas, Nonhlanhla Ntuli

“…Previous studies show that the discursive production of oral narratives impacts the development and use of higher-order language processing, as they require the knowledge, language skills and abilities to produce coherent discourse. …”
Get full text

Tibyan corpus: balanced and comprehensive error coverage corpus using ChatGPT for Arabic grammatical error correction by Ahlam Alrehili, Areej Alhothali

“…Natural language processing (NLP) augments text data to overcome sample size constraints. …”
Get full text