Natural Language Research Articles

Smart Caption: Intelligent Image Description Using Transformer Decoder

The need for automated image description systems has grown significantly with the rise of multimedia content across diverse domains such as social media, digital libraries, and accessibility technologies. Smart Caption presents a novel approach for generating intelligent and context-aware image descriptions by utilizing a combination of Vision Transformers (ViTs) and Natural Language Processing (NLP) Transformer decoders. Unlike traditional convolution-based methods, Vision Transformers treat images as sequences of patches, enabling them to capture global image features more effectively. These extracted visual features are then processed by a Transformer-based decoder to produce coherent and contextually appropriate captions, bridging the gap between image recognition and natural language generation. Our approach focuses on leveraging the attention mechanisms inherent in both Vision and NLP Transformers to enhance the quality of image descriptions. The ViT architecture is designed to focus on relevant regions within an image, while the NLP Transformer decoder is adept at generating fluent and detailed descriptions by attending to the most significant visual features. This two-stage process improves the precision of object detection, relationship understanding, and scene context in generated captions. Experimental results demonstrate that Smart Caption out performs traditional methods in terms of accuracy, contextual relevance, and fluency, marking a significant step forward in the field of automated image captioning. Through this research, we aim to provide a scalable, efficient, and intelligent solution for image description, with potential applications in areas such as accessibility tools for visually impaired users, digital content indexing, and automated content generation. Our findings highlight the strengths of transformer-based models in bridging vision and language tasks, offering promising directions for future research in multimodal AI..

Beyond Automation: A Rigorous Testing Framework for Reliable AI Chatbots in Life Insurance

AI-driven chatbots are transforming customer service in Life Insurance, offering policyholders instant support, streamlined inquiries, and personalized recommendations. However, deploying these chatbots effectively requires addressing unique challenges, including interpreting complex insurance terminology, ensuring regulatory compliance, and maintaining data security and user privacy. This research introduces a detailed testing framework specifically tailored to Life Insurance chatbots, covering functional, non-functional, AI-specific, and compliance testing to guarantee accuracy, reliability, and adherence to legal standards. The framework emphasizes essential practices for verifying natural language understanding, sensitive data handling, and empathetic responses for users navigating critical life events. This research highlights the critical role of targeted testing to deliver robust, user-centered chatbot solutions in the Life Insurance sector.

Moving towards the use of artificial intelligence in pain management.

While the development of artificial intelligence (AI) technologies in medicine has been significant, their application to acute and chronic pain management has not been well characterized. This systematic review aims to provide an overview of the current state of AI in acute and chronic pain management. This review was registered with PROSPERO (ID# CRD42022307017), the international registry for systematic reviews. The search strategy was prepared by a librarian and run in four electronic databases (Embase, Medline, Central, and Web of Science). Collected articles were screened by two reviewers. Included studies described the use of AI for acute and chronic pain management. From the 17,601 records identified in the initial search, 197 were included in this review. Identified applications of AI were described for treatment planning as well as treatment delivery. Described uses include prediction of pain, forecasting of individualized responses to treatment, treatment regimen tailoring, image-guidance for procedural interventions and self-management tools. Multiple domains of AI were used including machine learning, computer vision, fuzzy logic, natural language processing and expert systems. There is growing literature regarding applications of AI for pain management, and their clinical use holds potential for improving patient outcomes. However, multiple barriers to their clinical integration remain including lack validation of such applications in diverse patient populations, missing infrastructure to support these tools and limited provider understanding of AI. This review characterizes current applications of AI for pain management and discusses barriers to their clinical integration. Our findings support continuing efforts directed towards establishing comprehensive systems that integrate AI throughout the patient care continuum.

The Geometry and Dynamics of Meaning.

An enigma for human languages is that children learn to understand words in their mother tongue extremely fast. The cognitive sciences have not been able to fully understand the mechanisms behind this highly efficient learning process. In order to provide at least a partial answer to this problem, I have developed a cognitive model of the semantics of natural language in terms of conceptual spaces. I present a background to conceptual spaces and provide a brief summary of their main features, in particular how it handles learning of concepts. I then apply the model to give a geometric account of the semantics of different word classes. In particular, I propose a "single-domain hypotheses" for the semantics of all word classes except nouns. These hypotheses provide a partial answer to the enigma of how words are learned. Next, a dynamic cognitive model of events is introduced that replaces and extends the function of thematic roles. I apply it to analyze the meanings of different kinds of verbs. I argue that the model also explains some aspects of syntactic structure. In particular, I propose that a sentence typically refers to an event. Some further applications of conceptual spaces are briefly presented.

AI Virtual Assistants in Human Services: Empowering Customers and Caseworkers

Abstract—This paper explores the transformative role of AI virtual assistants (VAs) in human services, highlighting their potential to enhance communication, streamline processes, and improve customers’ and caseworkers' overall experience. By examining technology applications and challenges, the aim is to comprehensively understand how VAs can empower the human services industry. Keywords—AI Virtual assistant, Natural language Processing, Machine learning, Caseworker assistant, Customer assistant

Personalized Emotion Detection Adapting Models to Individual Emotional Expressions

Emotion recognition from text and speech has become a critical area of research in artificial intelligence (AI), enhancing human-computer interaction across various sectors. This paper explores the methodologies used in emotion recognition, focusing on Natural Language Processing (NLP) for text and acoustic analysis for speech. It reviews key machine learning and deep learning models, including Support Vector Machines (SVM), neural networks, and transformers, and highlights the datasets commonly used in emotion detection studies. The paper also addresses challenges such as multimodal integration, data ambiguity, and ethical considerations like privacy concerns and bias in models. Applications in customer service, healthcare, education, and entertainment are discussed, showcasing the growing importance of emotion recognition in AI- driven systems. Future research directions, including advancements in deep learning, multimodal systems, and real-time processing, are also explored to address existing limitations.

DeepFake Image Detection: Fake Image Detection using CNNs and GANs Algorithm

Deep learning is a powerful and versatile technique that has seen extensive applications in areas such as natural language processing, machine learning, and computer vision. Among its most recent applications is the generation of deepfakes, which are high-quality, realistic altered videos or images that have garnered significant attention. While innovative uses of deepfake technology are being explored, its potential for misuse has raised serious concerns. Harmful applications, such as spreading fake news, creating celebrity pornography, financial fraud, and revenge pornography, have become increasingly prevalent in the digital age. As a result, public figures, including celebrities and politicians, face heightened risks from deepfake content. In response, substantial research has been conducted to explore the mechanics behind deepfakes, leading to the development of various deep learning-based algorithms for their detection. This study provides a comprehensive review of deepfake creation and detection techniques, focusing on different deep learning approaches. Additionally, it discusses the limitations of existing methods and the availability of datasets for research. The lack of a highly accurate and fully automated deepfake detection system presents a significant challenge as the ease of generating and distributing such content continues to grow. Nonetheless, recent efforts in deep learning have shown promising results, surpassing traditional detection methods.

Post-marketing surveillance of anticancer drugs using natural language processing of electronic medical records

This study demonstrates that adverse events (AEs) extracted using natural language processing (NLP) from clinical texts reflect the known frequencies of AEs associated with anticancer drugs. Using data from 44,502 cancer patients at a single hospital, we identified cases prescribed anticancer drugs (platinum, PLT; taxane, TAX; pyrimidine, PYA) and compared them to non-treatment (NTx) group using propensity score matching. Over 365 days, AEs (peripheral neuropathy, PN; oral mucositis, OM; taste abnormality, TA; appetite loss, AL) were extracted from clinical text using an NLP tool. The hazard ratios (HRs) for the anticancer drugs were: PN, 1.15–1.95; OM, 3.11–3.85; TA, 3.48-4.71; and AL, 1.98–3.84; the HRs were significantly higher than that of the NTx group. Sensitivity analysis revealed that the HR for TA may have been underestimated; however, the remaining three types of AEs extracted from clinical text by NLP were consistently associated with the three anticancer drugs.

Mini-mental status examination phenotyping for Alzheimer's disease patients using both structured and narrative electronic health record features.

This study aims to automate the prediction of Mini-Mental State Examination (MMSE) scores, a widely adopted standard for cognitive assessment in patients with Alzheimer's disease, using natural language processing (NLP) and machine learning (ML) on structured and unstructured EHR data. We extracted demographic data, diagnoses, medications, and unstructured clinical visit notes from the EHRs. We used Latent Dirichlet Allocation (LDA) for topic modeling and Term-Frequency Inverse Document Frequency (TF-IDF) for n-grams. In addition, we extracted meta-features such as age, ethnicity, and race. Model training and evaluation employed eXtreme Gradient Boosting (XGBoost), Stochastic Gradient Descent Regressor (SGDRegressor), and Multi-Layer Perceptron (MLP). We analyzed 1654 clinical visit notes collected between September 2019 and June 2023 for 1000 Alzheimer's disease patients. The average MMSE score was 20, with patients averaging 76.4 years old, 54.7% female, and 54.7% identifying as White. The best-performing model (ie, lowest root mean squared error (RMSE)) is MLP, which achieved an RMSE of 5.53 on the validation set using n-grams, indicating superior prediction performance over other models and feature sets. The RMSE on the test set was 5.85. This study developed a ML method to predict MMSE scores from unstructured clinical notes, demonstrating the feasibility of utilizing NLP to support cognitive assessment. Future work should focus on refining the model and evaluating its clinical relevance across diverse settings. We contributed a model for automating MMSE estimation using EHR features, potentially transforming cognitive assessment for Alzheimer's patients and paving the way for more informed clinical decisions and cohort identification.

The impact of AI-enhanced natural language processing tools on writing proficiency: an analysis of language precision, content summarization, and creative writing facilitation

The impact of AI-enhanced natural language processing tools on writing proficiency: an analysis of language precision, content summarization, and creative writing facilitation

IndoGovBERT: A Domain-Specific Language Model for Processing Indonesian Government SDG Documents

Achieving the Sustainable Development Goals (SDGs) requires collaboration among various stakeholders, particularly governments and non-state actors (NSAs). This collaboration results in but is also based on a continually growing volume of documents that needs to be analyzed and processed in a systematic way by government officials. Artificial Intelligence and Natural Language Processing (NLP) could, thus, offer valuable support for progressing towards SDG targets, including automating the government budget tagging and classifying NSA requests and initiatives, as well as helping uncover the possibilities for matching these two categories of activities. Many non-English speaking countries, including Indonesia, however, face limited NLP resources, such as, for instance, domain-specific pre-trained language models (PTLMs). This circumstance makes it difficult to automate document processing and improve the efficacy of SDG-related government efforts. The presented study introduces IndoGovBERT, a Bidirectional Encoder Representations from Transformers (BERT)-based PTLM built with domain-specific corpora, leveraging the Indonesian government’s public and internal documents. The model is intended to automate various laborious tasks of SDG document processing by the Indonesian government. Different approaches to PTLM development known from the literature are examined in the context of typical government settings. The most effective, in terms of the resultant model performance, but also most efficient, in terms of the computational resources required, methodology is determined and deployed for the development of the IndoGovBERT model. The developed model is then scrutinized in several text classification and similarity assessment experiments, where it is compared with four Indonesian general-purpose language models, a non-transformer approach of the Multilabel Topic Model (MLTM), as well as with a Multilingual BERT model. Results obtained in all experiments highlight the superior capability of the IndoGovBERT model for Indonesian government SDG document processing. The latter suggests that the proposed PTLM development methodology could be adopted to build high-performance specialized PTLMs for governments around the globe which face SDG document processing and other NLP challenges similar to the ones dealt with in the presented study.

MeDi‐TODER: Medical Domain‐Incremental Task‐Oriented Dialogue Generator Using Experience Replay

ABSTRACTArtificial intelligence (AI) technology has brought groundbreaking changes to the healthcare domain. Specifically, the integration of a medical dialogue system (MDS) has facilitated interactions with patients, identifying meaningful information such as symptoms and medications from their dialogue history to generate appropriate responses. However, shortcomings arise when MDS lacks access to the patient's cumulative history or prior domain knowledge, resulting in the generation of inaccurate responses. To address this challenge, we propose a medical domain‐incremental task‐oriented dialogue generator using experience replay (MeDi‐TODER) that applies the continual learning technique to the medical task‐oriented dialogue generator. By strategically sampling and storing exemplars from previous domains and rehearsing it as it learns, the model effectively retains knowledge and can respond to the novel domains. Extensive experiments demonstrated that MeDi‐TODER significantly outperforms other models that lack continual learning in both natural language generation and natural language understanding. Notably, our proposed method achieves the highest scores, surpassing the upper‐class benchmarks.

Impacts of interacting with an AI chatbot on preservice teachers' responsive teaching skills in math education

AbstractBackgroundArtificial Intelligence (AI) technologies offer unique capabilities for preservice teachers (PSTs) to engage in authentic and real‐time interactions using natural language. However, the impact of AI technology on PSTs' responsive teaching skills remains uncertain.ObjectivesThe primary objective of this study is to examine whether interaction with a responsive AI‐based chatbot that acts as a virtual student improves pre‐service teachers' noticing abilities. The second objective is to compare how the presence or absence of chatbot responses affects changes in PSTs' questioning practices. Finally, the third objective is to investigate how the experience of interacting with the responsive virtual student affects PSTs' perceptions of the effectiveness of their questioning, their satisfaction with the interactions, and their confidence about interacting with a real student compared to the non‐responsive chatbot.MethodsA randomised controlled pre‐ and post‐test design was used with 50 PSTs. PSTs' noticing, interaction with the chatbot, and post‐survey data were collected, and a t‐test was conducted to examine significant differences by group.Results and ConclusionIn the experimental group, the virtual student responded to PSTs' questions, while in the control group, she did not. Notable differences were observed in their questioning practices.TakeawaysOverall, AI‐based chatbots hold promise for enhancing PSTs' responsive teaching skills. Future research is needed to examine the long‐term impact of responsive chatbot use on PSTs' noticing skills.

Deep Learning for Text Sentiment Analysis: A Survey

Abstract. With the continuous improvement of many factors such as corpus, computing power, data scale, and laboratory conditions, how to quickly and accurately understand the emotional tendency in the text has become an important issue in many fields. The current state of affairs and the trajectory that deep learning is pursuing in the realm of text emotion analysis hold significant importance. This article first introduces the definition, importance and classification of emotional analysis, including the analysis of emotional polarity, emotional detection and fine-grained emotion. Subsequently, the key technologies of deep learning were discussed and the application of deep learning in natural language processing, especially LSTM, Bert, and their specific applications in emotional analysis within deep learning models. Then reveal the advantages and limitations of each model by comparing the performance of different deep learning models in emotional analysis tasks. Finally, in combination with current deep learning research, this study summarizes the challenges and research trends in the field of text emotional analysis.

Investigating Open Source LLMs to Retrofit Competency Questions in Ontology Engineering

Competency Questions (CQs) are essential in ontology engineering; they express an ontology's functional requirements as natural language questions, offer crucial insights into an ontology's scope and are pivotal for various tasks, e.g. ontology reuse, testing, requirement specification, and pattern definition. Despite their importance, the practice of publishing CQs alongside ontological artefacts is not commonly adopted. We propose an approach based on Generative AI, specifically Large Language Models (LLMs) for retrofitting CQs from existing ontologies and we investigate how open LLMs (i.e. Llama-2-70b, Mistral 7B and Flan-T5-xl) perform in generating CQs for existing ontologies. We compare these results with our previous efforts using closed-source LLMs and we reflect on the results.

AI-Driven Optimization of Financial Quantitative Trading Algorithms and Enhancement of Market Forecasting Capabilities

Abstract: The application of artificial intelligence (AI) into financial markets has revolutionised quantitative trading and market forecasting by increasing the efficiency of algorithmic trading, improving the accuracy of market predictions and facilitating real-time market decisions. This paper will provide an overview of the application of Al in the financial markets focusing on the use of machine learning (ML), deep learning (DL) and reinforcement learning (RL) in optimizing the trading algorithms, specifically the capability of Al to process very high data points and complex relationships that other quantitative models are unable to capture. We will discuss trading algorithms such as XGBoost, deep neural networks such as long short-term memory (LSTM) networks and convolutional neural networks (CNNs), how they can outperform traditional quantitative trading models and real-time decision making in stock price prediction, pattern recognition and trading strategy optimisation. We will also look at Al-enhanced predictive models that utilise deep learning and layered models, such as Natural language processing (NLP) sentiment analysis to capture the public sentiment in the market to forecast employing diverse datasets such as historical prices, market volatility, macroeconomic factors and social media sentiment to improve the forecasting accuracy. By going through several experiments and case studies, this paper will shed light on the impact of entrusting quantitative trading and market forecasting decisions to AI for improved performance and reduced errors. There are many challenges ahead but AI plays a constructive role in improving the trading strategies and forecasting market outcomes accurately.

AI Use in Application Modernization for Banking Applications

Implementing Artificial Intelligence (AI) and machine Learning (ML) into application modernization will shake up various industries, including finance, healthcare, manufacturing, e-commerce, and retail. This white paper will analyze the transformative potential of AI and ML in modernizing legacy systems and applications, enhancing innovation, operational efficiency, and security during modernization. By leveraging AI technologies like machine learning, natural language processing, and deep learning, organizations can streamline processes, enhance decision- making in the planning phase, and reduce errors during application modernization. The paper also addresses the challenges and considerations in planning and implementing application modernization in banks, as AI and ML have been increasingly adopted in the banking sector. AI and ML help with planning in Hollow the core, including data privacy, ethical concerns, and the need for a skilled workforce.

A study of machine learning applications in healthcare

Abstract. Machine learning, a sub-field of artificial intelligence, has numerous algorithms with applications in image recognition and classification, natural language processing, data prediction, medical diagnosis, and more, achieving significant results. Nowadays, the application of many algorithms of machine learning in the medical field has become a research hotspot and attracted wide attention from society, which plays a key role in disease screening, disease prediction, and assisted diagnosis of diseases. In this paper, we have developed a new approach to the medical field that can be applied in the healthcare industry by using technologies such as k-nearest neighbor (KNN), recurrent neural network (RNN), plain Bayesian (NB), decision tree (DTT), random forest (RF), deep convolutional adversarial network (DCAN), generative adversarial network (GAN), deep convolutional generative adversarial network (DCGAN),deep convolutional neural network (CNN), and support vector machine (SVM). By referring to the existing related literature and application practice results, this paper provides a systematic introduction to the application and research of machine learning in the medical field. This paper also analyses and describes the challenges and difficulties in the implementation of machine learning in the medical field.

Integrating AI into Agile Workflows: Opportunities and Challenges

Abstract: Over the past few years, Agile development approaches have become an increasingly popular methodology for software engineering, focused on iterative progress, continuous feedback, and teamwork cooperation. However, the raising difficulties of projects and more demand for faster and more efficient workflows have challenged the situation further. The introduction of Artificial Intelligence into the Agile processes paves the way to optimize decision-making, automate routine tasks, and boost team productivity. This review summarizes the innovations and challenges created by the integration of AI into Agile development practices. Using AI technologies like machine learning, predictive analysis, and natural language processing, Agile teams can enhance sprint planning, resource coordination, and risk management. Also, it presents some risks such as data privacy, workforce skills need, and possible over-dependence of AI. The paper emphasizes on providing a full overview of the innovations and challenges to the application of AI in Agile workflows, providing thoughts for future research and practices.

Quantum mechanics and statistical physics: Novel frameworks for enhancing natural language processing

Abstract. This article explores the pioneering application of principles from quantum mechanics and statistical mechanics to the field of natural language processing (NLP). By drawing analogies between physical phenomena such as quantum entanglement, phase transitions, and statistical ensembles, and linguistic concepts like semantic relationships, language use dynamics, and lexical diversity, we offer a novel perspective on language analysis and processing. Quantum linguistic models, leveraging the intricacies of entanglement and quantum probability, provide a framework for understanding complex semantic networks and enhancing computational efficiency through quantum computing. Meanwhile, statistical mechanics inspires models for capturing lexical diversity and understanding the evolution of language patterns, akin to phase transitions in physical systems. This interdisciplinary approach not only deepens our understanding of linguistic phenomena but also introduces advanced mathematical and computational techniques to improve NLP tasks.