Language Processing Research Articles

An Analysis of Knowledge Management Changes Through Artificial Intelligence with Probst's Model

In recent years, the integration of Artificial Intelligence (AI) into Knowledge Management (KM) has led to transformational changes. These changes have significantly enhanced traditional KM processes. To identify how AI technologies improve and reshape knowledge processes, this study conducted a systematic literature review. The review identified AI technologies suitable for each of Probst's building blocks, which outline the eight central KM processes. The research reveals a wide range of AI technologies, including machine learning, natural language processing and chatbots such as ChatGPT. These technologies can be applied in different domains and introduce innovative approaches to improve KM processes. Based on the AI technologies analysed, this study proposes a four-stage model to support the documentation and application of best practices and lessons learned. The model is designed to enhance the knowledge development process and aims to document and secure key project developments in the long term. A further objective was to analyse which KM process is most affected by chatbots. The findings indicate that chatbots have the potential to transform the use of knowledge in organisations. They act as facilitators by breaking down existing barriers, foster an open culture of knowledge sharing, streamline workflows and increase the accessibility of knowledge. The study also examines the broader changes that AI will bring to KM and forecasts the sixth generation of KM. It draws on Bencsik's (2021) evolutionary and revolutionary perspectives that specifically forecast this next generation. The study shows that AI not only enhances existing KM processes but also has the potential to fundamentally disrupt traditional methods and approaches. These findings underline the need for future research to explore the effective integration and scalability of AI technologies in real-world KM environments. This will help ensure that their long term impact and potential benefits are fully understood across different industries and organisational contexts.

TokChat: Tokenization of Text for Secured Peer-to-Peer Communication

This paper presents TokChat, a system that utilizes a new approach designed for enhanced security in peer-to-peer communication using text messages. To improve the security of messages in a conversation, the system converts a message into tokens by leveraging existing pre-trained tokenizers that are commonly used across numerous natural language processing (NLP) tasks. The tokens represent a compact numerical form of text that captures the original message. A new private key is generated for every new conversation to ensure the confidentiality of the messages in the conversation. The tokens are encrypted using an existing AES-based cryptographic encryption approach, ensuring they can be securely transmitted to the recipient. The receiver receives the encrypted tokens, which are decrypted using the conversation-specific key. The decrypted tokens are converted to readable text using the tokenizer. The usage of the system ensures that the messages fail to be converted into readable text by successful attackers, even with the usage of the private conversation-specific key, without being aware of the tokenization process. The system offers a higher security standard for secure messaging in the use cases in which the confidentiality of the messages is crucial. The system has been tested using multiple text values and successfully tokenized the text, encrypted the tokens, decrypted the transmitted ciphertext, and reproduced the original text. The code is available at github.com/Pro-GenAI/TokChat. Keywords: natural language processing (NLP), tokenization, cryptographic messaging, secure communication

Tokenization Beyond NLP: Potential Applications in Data Analytics, Cybersecurity, and Beyond

Tokenization is the process of segmenting redundant patterns of input data, such as text, into tokens that are suitable for model training and computational analysis. Tokenization plays a foundational role in Natural Language Processing (NLP). Additionally, tokenization methods exhibit significant potential in domains outside of NLP, where combining redundant patterns in data can enhance the efficiency, scalability, analytical capabilities, and accuracy of predictions. This paper explores the potential applications of tokenization in fields beyond NLP in multiple areas, including but not limited to bioinformatics, cybersecurity, and healthcare. These applications demonstrate the ability of tokenization to simplify complex data patterns, thereby enhancing predictive accuracy. By leveraging the pattern recognition strengths of tokenization, multiple domains could receive benefits from efficient data processing and pattern recognition, which indicates a promising future for custom tokenization techniques across disciplines. Keywords: Pattern Recognition, tokenization, tokens, Machine Learning (ML), Natural Language Processing (NLP)

AI-Powered VR for Enhanced Learning Compared to Traditional Methods

This paper evaluates a VR (Virtual Reality) application aimed at enhancing the learning of Python collection data types and structures for electrical and electronic engineering students. By incorporating gamification and personalisation features, the application provides an immersive environment where students can interact with virtual representations of complex programming concepts. To further enhance interactivity and engagement, the application integrates a virtual assistant and example generator, developed using Meta Voice SDK (Software Development Kit) and wit.ai. These AI (Artificial Intelligence)-NLP (Natural Language Processing) tools create personalised learning paths and generate dynamic examples based on individual learning progress. A user study was conducted with a total of 48 participants. During the user study, participants were divided into two equal groups of 24, both wearing EEG (Electroencephalography) headsets: one group engaged with the VR application, while the other read the traditional booklet, allowing for the recording and analysis of attention and engagement levels. These measures of engagement and attention were then compared to those extracted from a benchmark cohort of students whose learning experience was through more traditional booklets. The results indicated a statistically significant improvement in understanding Python collections among VR users compared to their baseline scores, highlighting the benefits of interactive and tailored learning environments. Additionally, EEG data analysis showed that VR users exhibited higher average levels of attention and engagement compared to those using the paper-based method, demonstrating the effectiveness of immersive technologies in sustaining learner interest and focus, particularly in enhancing learning for software development.

AI-Based Medical Data Mining

The analysis of real-time medical data is a transformative approach that combines machine learning, natural language processing, and web scraping technologies to offer timely, accurate, and relevant information for healthcare decision-making. This paper presents a system that, when given a medical keyword as input, system retrieves the top Google links, assesses the content for accuracy, and organizes the data into a structured way. The system also summarizes the information into concise, digestible points for quick reference. This work provides healthcare professionals, researchers, and policymakers with a powerful tool for retrieving, analyzing, and synthesizing real-time online medical data.

Automated derivation of diagnostic criteria for lung cancer using natural language processing on electronic health records: a pilot study

BackgroundThe digitisation of healthcare records has generated vast amounts of unstructured data, presenting opportunities for improvements in disease diagnosis when clinical coding falls short, such as in the recording of patient symptoms. This study presents an approach using natural language processing to extract clinical concepts from free-text which are used to automatically form diagnostic criteria for lung cancer from unstructured secondary-care data.MethodsPatients aged 40 and above who underwent a chest x-ray (CXR) between 2016 and 2022 were included. ICD-10 and unstructured data were pulled from their electronic health records (EHRs) over the preceding 12 months to the CXR. The unstructured data were processed using named entity recognition to extract symptoms, which were mapped to SNOMED-CT codes. Subsumption of features up the SNOMED-CT hierarchy was used to mitigate against sparse features and a frequency-based criteria, combined with univariate logarithmic probabilities, was applied to select candidate features to take forward to the model development phase. A genetic algorithm was employed to identify the most discriminating features to form the diagnostic criteria.Results75002 patients were included, with 1012 lung cancer diagnoses made within 12 months of the CXR. The best-performing model achieved an AUROC of 0.72. Results showed that an existing ‘disorder of the lung’, such as pneumonia, and a ‘cough’ increased the probability of a lung cancer diagnosis. ‘Anomalies of great vessel’, ‘disorder of the retroperitoneal compartment’ and ‘context-dependent findings’, such as pain, statistically reduced the risk of lung cancer, making other diagnoses more likely. The performance of the developed model was compared to the existing cancer risk scores, demonstrating superior performance.ConclusionsThe proposed methods demonstrated success in leveraging unstructured secondary-care data to derive diagnostic criteria for lung cancer, outperforming existing risk tools. These advancements show potential for enhancing patient care and results. However, it is essential to tackle specific limitations by integrating primary care data to ensure a more thorough and unbiased development of diagnostic criteria. Moreover, the study highlights the importance of contextualising SNOMED-CT concepts into meaningful terminology that resonates with clinicians, facilitating a clearer and more tangible understanding of the criteria applied.

Governance Considerations of Adversarial Attacks on AI Systems

Artificial intelligence (AI) is increasingly integrated into various aspects of daily life, but its susceptibility to adversarial attacks poses significant governance challenges. This paper explores the nature of these attacks, where malicious actors manipulate input data to deceive AI algorithms and their profound implications for individuals and society. Adversarial attacks can undermine critical AI applications, such as facial recognition and natural language processing, leading to privacy violations, biased outcomes, and eroding public trust. The discussion emphasizes understanding the threat vectors associated with adversarial attacks and their potential repercussions. It advocates for robust governance frameworks encompassing risk management, oversight, and legislative measures to protect AI systems. Such frameworks should prioritize AI technologies' confidentiality, integrity, and availability (CIA) while ensuring compliance with ethical standards. Furthermore, the paper examines various strategies for mitigating risks associated with adversarial attacks, including training and continuous monitoring of AI systems. It highlights the importance of accountability among developers and researchers in implementing preventive measures that align with principles of transparency and fairness. Organizations can enhance security and foster public trust by integrating legislative frameworks into AI development standards. As AI technologies evolve, continuous review of governance practices is essential to address emerging threats effectively. This paper ultimately focuses on the critical role of comprehensive governance in safeguarding AI systems against adversarial attacks, ensuring that technological advancements benefit society while minimizing risks.

HealthSphere: Integrated AI-Powered and Blockchain Based Health Management and Support System

The healthcare sector is undergoing a significant transformation as it embraces advanced technologies to address some of the most pressing challenges related to accessibility, data security, and operational efficiency. Among these innovations, Artificial Intelligence (AI) and Blockchain technology have emerged as key enablers of enhanced healthcare delivery. AI-powered chatbots are being increasingly utilized to provide immediate, real-time assistance to patients, helping them assess symptoms, obtain basic medical advice, and access information without the need for in-person consultations. These chatbots, powered by Natural Language Processing (NLP) and Machine Learning (ML) algorithms, can efficiently handle a wide range of patient inquiries, improving accessibility and reducing the burden on healthcare providers. On the other hand, Blockchain technology is revolutionizing the way health records are managed. It offers a decentralized, secure, and transparent method of storing and sharing health data, ensuring data integrity, and empowering patients with control over their own medical information. By enabling smart contracts and secure data transactions, Blockchain ensures that health records are easily shared among authorized entities, reducing the risks of unauthorized access and data breaches. This paper provides an in-depth survey of the integration of these technologies into a unified healthcare management system. It explores the practical applications of AI chatbots in improving patient engagement, symptom management, and appointment scheduling, while also discussing how Blockchain can enhance the security, transparency, and interoperability of health records. The paper further addresses the challenges that come with implementing these technologies, including issues related to scalability, data privacy, and regulatory compliance. Finally, it proposes a scalable, secure, and user-friendly platform that combines the strengths of both AI chatbots and Blockchain to create an efficient and reliable healthcare system, poised to improve the overall delivery of healthcare services..

Sound Symbolism in the Lexicon: A Review of Iconic‐Systematicity

ABSTRACTSound symbolism refers to associations between language sounds (i.e., phonemes) and particular properties (e.g., certain shapes). For example, phonemes like /m/ are associated with roundness, while phonemes like /k/ are associated with spikiness. In this paper I review the accumulating evidence that different instances of sound symbolism can be observed as patterns in real words in existing lexicons (e.g., /m/ occurring more frequently in words for round things). The properties examined include shape, size, texture, valence and arousal. Such effects are an instance of both iconicity (words whose forms resemble their meanings) and systematicity (largescale patterns in the forms of related words in a language). I also discuss open questions on the topic, including how such patterns emerge, and their effects on language processing.

Future Prospects of Large Language Models: Enabling Natural Language Processing in Educational Robotics

Large language models (LLMs) have recently shown considerable promise in educational robotics by offering generic knowledge necessary in situations when prior programming is not possible. In general, mobile education robots cannot perform tasks like navigation or localization unless they have a working knowledge of maps. In this letter, we tackle the issue of making LLMs more applicable in the field of mobile education robots by helping them to understand Space Graph, a text-based map description. This study, which focuses on LLMs, is divided into several sections. It explores basic natural language processing (NLP) techniques and highlights how they can help create smooth education discussions. Examining the development of LLMs inside NLP systems, the paper explores the benefits and implementation issues of important models utilized in the education sector. Applications useful in educational discussions are described in depth, ranging from patient-focused tools like diagnosis and treatment recommendations to systems that support education providers. We provide thorough instructions and real-world examples for quick engineering, making LLM-based educational robotics solutions more accessible to novices. We demonstrate how LLM-guided upgrades can be easily included in education robotics applications using tutorial-level examples and structured prompt creation. This survey provides a thorough review and helpful advice for leveraging language models in automation development, acting as a road map for researchers navigating the rapidly changing field of LLM-driven educational robotics.

Second language learning of degree expressions: A computational approach

Abstract Degrees, unlike entities or events, refer to comparative qualities and are closely tied to gradable adjectives such as “tall.” Degree expressions have been explored in second language (L2) research, covering areas such as learnability, first language (L1) transfer, contrastive analysis, and acquisition difficulty. However, a computational approach to the learning of degree expressions in L2 contexts, particularly for L1 Chinese learners of English, has not been thoroughly investigated. This study aims to fill this gap by utilizing natural language processing (NLP) methods, drawing insights from recent advancements in large language models (LLMs). This study extends Cong (2024)’s general-purpose assessment pipeline to specifically analyze degree expressions, predicting that surprisal metrics will correlate with proficiency levels and distinct developmental stages of L2 learners. Crucially, we address the limitations of surprisal metrics in capturing underuse or avoidance—common in L2 development—by integrating frequency-based analyses. Using an NLP pipeline developed with Stanza, we automatically identified and analyzed degree expressions, constructing linear mixed-effects models to track L2 development trajectories. Our findings reveal that as proficiency increases, learners use complex degree expressions more frequently, supporting theories linking difficulty and learnability. Higher surprisal values are associated with lower proficiency in using degree expressions, and these surprisals are more predictive of degree expressions proficiency than classic NLP measures. These results add further evidence that LLMs and NLP tools provide valuable insights into L2 development, specifically in the domain of degree expressions, expanding upon previous research and offering new approaches for understanding L2 learning processes.

AI-Enhanced Cloud Security: Proactive Threat Detection and Response Mechanisms

AI-enhanced cloud security is revolutionizing the way organizations approach cybersecurity by leveraging advanced technologies like machine learning, natural language processing, and deep learning to proactively detect and respond to cyber threats. This paper explores the integration of AI into cloud security systems, highlighting its role in improving threat detection accuracy, reducing response times, and enhancing data protection across cloud environments. The paper also examines various AI-driven tools such as intrusion detection systems, behaviour analytics, and automated threat response mechanisms, which provide real-time defence capabilities. Despite its potential, the adoption of AI in cloud security faces challenges, including data privacy concerns, algorithmic bias, integration with legacy systems, and the high computational costs associated with AI models. Furthermore, ethical, and regulatory challenges complicate the deployment and scalability of AI in cloud security. By addressing these challenges and fostering continuous innovation, organizations can unlock the full potential of AI-enhanced security systems. This paper aims to provide a comprehensive overview of the current state of AI-driven cloud security, identify the key challenges faced by organizations, and offer insights into future developments and opportunities in this rapidly evolving field.

Exploring Named Entity Recognition via MacBERT-BiGRU and Global Pointer with Self-Attention

Named Entity Recognition (NER) is a fundamental task in natural language processing that aims to identify and categorize named entities within unstructured text. In recent years, with the development of deep learning techniques, pre-trained language models have been widely used in NER tasks. However, these models still face limitations in terms of their scalability and adaptability, especially when dealing with complex linguistic phenomena such as nested entities and long-range dependencies. To address these challenges, we propose the MacBERT-BiGRU-Self Attention-Global Pointer (MB-GAP) model, which integrates MacBERT for deep semantic understanding, BiGRU for rich contextual information, self-attention for focusing on relevant parts of the input, and a global pointer mechanism for precise entity boundary detection. By optimizing the number of attention heads and global pointer heads, our model achieves an effective balance between complexity and performance. Extensive experiments on benchmark datasets, including ResumeNER, CLUENER2020, and SCHOLAT-School, demonstrate significant improvements over baseline models.

MAFD: Multiple Adversarial Features Detector for Enhanced Detection of Text-Based Adversarial Examples

Adversarial attacks in the field of Natural Language Processing greatly undermine the effectiveness and safety of models, raising significant challenges when it comes to real-world implementation. The researchers suggested using detection methods to identify and reject hostile samples while maintaining the accuracy of the original model. Nevertheless, current detection methods depend on analyzing a single characteristic, resulting in restricted resilience and flexibility. To address these constraints, we proposed the Multiple Adversarial Features Detector (MAFD), an innovative detection technique that utilizes a wide range of adversarial features, such as segmented perplexity, word frequency, and probability distribution, to enhance the effectiveness of detecting adversarial examples. Our comprehensive experiments shows that MAFD outperforms existing advanced methods in terms of detection accuracy and displays significant robustness and adaptability when applied to various base detectors and attack scenarios. In addition, the design of MAFD facilitates the seamless integration of further adversarial features, hence enhancing its detection capabilities.

Enhancing Email Security: A Real‐Time Machine Learning‐Based Spam Detection System

ABSTRACTSpam emails pose a persistent threat to online security and productivity. To combat this menace, we propose a robust machine learning‐based spam email detection system, leveraging algorithms like Naive Bayes, Support Vector Machine (SVM), and Random Forest (RF). Our system integrates Python's Natural Language Processing (NLP) library and cloud sourcing to achieve unparalleled accuracy and adaptability. Advanced feature extraction techniques, including Term Frequency‐Inverse Document Frequency (TF‐IDF) and N‐grams, enable comprehensive analysis of email content. Real‐time scanning and detection capabilities ensure immediate protection, while continuous learning allows the system to evolve and counter emerging spam tactics. Our system demonstrates exceptional performance, achieving accuracy rates of up to 97.58% with SVM. Comparative analysis of 11 machine learning algorithms reveals notable performance variations. By minimizing false positives and negatives, our system provides reliable protection against unwanted and harmful emails. This research contributes to the development of effective spam detection solutions, offering insights into optimal algorithms, time complexity‐accuracy trade‐offs, and scalable system design. Our system has significant implications for enhancing email security, safeguarding users from security breaches, and mitigating the economic impacts of spam.

LOGIC: LLM-originated guidance for internal cognitive improvement of small language models in stance detection.

Stance detection is a critical task in natural language processing that determines an author's viewpoint toward a specific target, playing a pivotal role in social science research and various applications. Traditional approaches incorporating Wikipedia-sourced data into small language models (SLMs) to compensate for limited target knowledge often suffer from inconsistencies in article quality and length due to the diverse pool of Wikipedia contributors. To address these limitations, we utilize large language models (LLMs) pretrained on expansive datasets to generate accurate and contextually relevant target knowledge. By providing concise, real-world insights tailored to the stance detection task, this approach surpasses the limitations of Wikipedia-based information. Despite their superior reasoning capabilities, LLMs are computationally intensive and challenging to deploy on smaller devices. To mitigate these drawbacks, we introduce a reasoning distillation methodology that transfers the reasoning capabilities of LLMs to more compact SLMs, enhancing their efficiency while maintaining robust performance. Our stance detection model, LOGIC (LLM-Originated Guidance for Internal Cognitive improvement of small language models in stance detection), is built on Bidirectional and Auto-Regressive Transformer (BART) and fine-tuned with auxiliary learning tasks, including reasoning distillation. By incorporating LLM-generated target knowledge into the inference process, LOGIC achieves state-of-the-art performance on the VAried Stance Topics (VAST) dataset, outperforming advanced models like GPT-3.5 Turbo and GPT-4 Turbo in stance detection tasks.

ENHANCING DEEP LEARNING PERFORMANCE THROUGH A GENETIC ALGORITHM-ENHANCED APPROACH: FOCUSING ON LSTM

Deep learning has shown remarkable success in various applications, such as image classification, natural language processing, and speech recognition. However, training deep neural networks is challenging due to their complex architecture and the number of parameters required. Genetic algorithms have been proposed as an alternative optimization technique for deep learning, offering an efficient alternative way to find an optimal set of network parameters that minimize the objective function. In this paper, we propose a novel approach integrating genetic algorithms with deep learning, specifically LSTM models, to enhance performance. Our method optimizes crucial hyper-parameters including learning rate, batch size, neuron count per layer, and layer depth through genetic algorithms. Additionally, we conduct a comprehensive analysis of how genetic algorithm parameters influence the optimization process and illustrate their significant impact on improving LSTM model performance. Overall, the presented method provides a powerful mechanism for improving the performance of deep neural networks, and; thus, we believe that it has significant potential for future applications in the artificial intelligence discipline.

RuGECToR: rule-based neural network model for russian language grammatical error correction

Grammatical Error Correction is one of the core Natural Language Processing tasks. At the moment, the open source state-of-the-art Sequence Tagger for English is GECToR model. For the Russian language, this problem does not have solutions with the same good results due to the lack of labeled datasets, therefore we decided to contribute to the aforementioned task. In this research, we described the process of creating a synthetic dataset and training a model on it. We adapt GECToR architecture for Russian language and call it RuGECToR. We use this architecture because, unlike Sequence-to-Sequence approach, it is easy to interpret and does not require a lot of training data. Our goal was to train the model in such a way that it does not adapt to a specific sample, but generalizes the morphological properties of the language. The presented model achieves an F0.5 of 82.5 on synthetic data and an F0.5 of 22.2 on RULEC dataset which was not in the training set.

AI Driven Animal Farming and Livestock Management System

AI-Driven Animal Farming and Livestock Management System represents a pivotal advancement in agricultural technology, promising to revolutionize traditional farming practices by integrating artificial intelligence (AI) into livestock management. This abstract presents an overview of the system's multifaceted capabilities, emphasizing its role in guiding animal farmers towards optimal livestock care, enhancing marketing strategies, and offering a suite of advanced functionalities. At its core, this system employs sophisticated AI algorithms like Natural Language Processing (NLP) and Convolutional Neural Networks (CNNs) to provide personalized guidance to animal farmers, ensuring they adhere to best practices in livestock care. Through real-time monitoring and data analysis, the system offers actionable insights into nutrition, health, and reproduction management, thereby maximizing the well-being and productivity of livestock. Furthermore, the System incorporates innovative features tailored to streamline marketing efforts. By analyzing market trends, consumer preferences, and supply chain dynamics, the system enables farmers to make informed decisions regarding product positioning, pricing strategies, and distribution channels, thereby enhancing market competitiveness and profitability

Using deep learning and word embeddings for predicting human agreeableness behavior

The latest advancements of deep learning have resulted in a new era of natural language processing. The machines now possess an unparallel ability to interpret and engage with various tasks such as text classification, content generation and natural language understanding. This development extended to the analysis of human behavior, where deep learning models are used to decode human personality. Due to the rise of social media, generating huge amounts of textual data that reshaped communication patterns. Understanding personality traits is a challenging topic which helps us to explore the patterns of thoughts, feelings and behaviors which are helpful for recruitment, career counselling and consumers’ behavior for marketing, etc. In this research study, the main aim is to predict the human personality trait of agreeableness showing whether a person is emotional who feels a lot or thinker who is logical and has rational thinking. This behavior leads to analyzing them as cooperative, friendly and respecting difference of views. For comprehensive empirical analysis, shallow machine learning models, ensemble models, and deep learning technique including state of the art transformer-based models are applied on real-world dataset of MBTI. For feature engineering, textual features of TF-IDF and POS tagging and word embeddings such as word2vec, glove and sentence embeddings are explored. The results analysis shows the highest performance 91.57% with sentence embeddings utilizing Bi-LSTM algorithm that highlights the power of this study as compared to existing studies in the relevant literature.