Advanced Natural Language Processing Research Articles

Kiki – A Virtual AI Desktop Aider

The research“Kiki” is a voice-controlled virtual desktop assistant designed to enhance user productivity and streamline interaction with desktop environments. Leveraging natural language processing (NLP) techniques, Kiki enables users to perform various tasks through voice commands, ranging from opening applications to searching the web and playing music. The system employs state-of-the-art language models to understand user queries and generate contextually relevant responses, providing a seamless and personalized user experience. Key functionalities include task automation, information retrieval, and web search, allowing users to execute commands efficiently and effortlessly. By combining advanced NLP capabilities with intuitive voice interaction, Kiki represents a significant advancement in desktop assistant technology, promising to reshape the way individuals interact with their computers.

Virtual Fitness Trainer Using AI: A Research Paper

Abstract: Our research delves into the creation of a Virtual Fitness Trainer using Artificial Intelligence (AI) to offer personalized workout guidance and real-time feedback. This project harnesses advanced computer vision, machine learning, and natural language processing techniques to develop an intelligent system capable of accurately detecting human poses, tracking exercise repetitions, and providing corrective feedback. Utilizing Python's OpenCV library to capture live webcam feeds, processed by MediaPipe's BlazePose tool for precise pose estimation, our application employs a novel topology with 33 keypoints, enhancing the accuracy of body movement analysis. The frontend interface, designed with Flask, HTML, CSS, and Bootstrap, ensures an intuitive user experience, allowing selection from various exercises such as squats, curls, jumping jacks, push-ups, lateral raises, and pull-ups. Each exercise page offers detailed instructions and demonstration videos for correct technique execution. The system processes live video streams frame-by-frame, converting them into formats suitable for pose analysis and accuracy assessment. BlazePose tracks user movements in real-time, displaying a 33-keypoint exoskeleton via OpenCV, aiding in understanding body movements and tracking progress through repetition counts. The system also provides real-time feedback on exercise form, suggesting corrective actions to optimize the workout and minimize injury risks. Our Virtual Fitness Trainer addresses the limitations of existing fitness apps by enabling accurate, independent home workouts, bridging the gap left by the absence of gyms and personal trainers. It highlights AI's potential in fitness, with future advancements expected to enhance gesture recognition, adaptive workout plans, and integration with biometric data from wearables. As AI algorithms evolve, the Virtual Fitness Trainer aims to become indispensable for achieving health and wellness goals, offering a convenient, engaging, and supportive platform.

Genie: Enhancing information management in the restaurant industry through AI-powered chatbot

In the dynamic restaurant industry, we introduce "Genie," an AI-powered chatbot, represents an advancement in customer service efficiency through technological innovation. Designed to enhance restaurant operations including order processing, reservations, and FAQs management, Genie leverages advanced Natural Language Processing (NLP) techniques. By converting input queries into word embeddings and applying a sophisticated tag classification system, Genie precisely interprets customer intents and generates accurate responses, thereby markedly improving the dining experience. Our thorough examination of various word embeddings and classifiers—Word2Vec, Glove, BERT, Gaussian Naive Bayes, XGB, Artificial Neural Networks (ANN), and Recurrent Neural Networks—revealed that the combination of Word2Vec and ANN is the most effective, achieving an impressive accuracy rate of 88.9 %. This discovery highlights Genie's capability to not only streamline restaurant operations but also enhance customer satisfaction by minimizing wait times and facilitating contactless service options. Additionally, this study enriches the understanding of AI's application in service industries and explores the potential future impact of generative AI technologies on chatbot interactions. As AI technology advances, its integration is essential for Genie to deliver increasingly personalized and dynamic customer experiences, aligning with the evolving demands of the digital era. This research emphasizes the transformative impact of AI in the restaurant industry, providing valuable insights into its practical applications and future prospects for automated customer service solutions.

OPTIMIZING LONG TEXT CLASSIFICATION PERFORMANCE THROUGH KEYWORD-BASED SENTENCE SELECTION: A CASE STUDY ON ONLINE NEWS CLASSIFICATION FOR INDONESIAN GDP GROWTH-RATE DETECTION

Efficiently managing lengthy textual data, particularly in online news, is crucial for enhancing the performance of long text classification. This study delves into innovative approaches to streamline the Gross Domestic Product (GDP) computation process by harnessing modern data analytics, Natural Language Processing (NLP), and online news sources. Leveraging online news data introduces real-time information, promising to improve the accuracy and timeliness of economic indicators like GDP. However, handling the complexity of extensive textual data poses a challenge, demanding advanced NLP techniques. This research shifts from traditional word-weight-based methods to keyword-based extractive summarization techniques to address this. These tailored approaches ensure that selected sentences align precisely with specific keywords relevant to the research case, such as GDP growth rate detection. The study emphasizes the necessity of adapting summarization methods to capture information in unique research contexts effectively. According to classification results, the implementation of sentence selection successfully demonstrated improved performance in terms of classification accuracy. Specifically, there was an average accuracy increase of 0.0226 for machine learning and 0.0164 for transfer learning models. Additionally, in terms of computational efficiency, sentence selection also accelerates processing time during hyperparameter tuning and fine-tuning, as observed using the same computational resources.

Enhancing Non-player Characters in Unity 3D using GPT-3.5

This case study presents a comprehensive integration process of OpenAI's GPT-3.5 large language model (LLM) into Unity 3D to enhance non-player characters (NPCs) in video games and interactive applications. The study aims to develop an architecture and open-source software framework that enables NPCs to engage in dynamic real-time interactions with players and other characters. The background and motivation for the study are provided, highlighting the existing limitations of traditional NPC programming and the potential of advanced natural language models such as GPT-3.5 to overcome these limitations. The methodology section outlines the step-by-step process, covering framework design and preparation, core architecture development, humanoid avatar integration and animation, and important feature extensions. The progression of framework design and implementation is described, emphasizing key architectural concepts, design patterns, and essential classes and interfaces. The results of the case study are discussed, focusing on the valuable insights gained and the implications for future advancements. Lessons learned from the integration process are shared, along with suggestions for potential improvements and directions for future research. This case study provides a practical resource for game developers and researchers interested in leveraging advanced natural language processing capabilities to create more immersive and interactive NPC experiences in Unity 3D environments.

CareerBoost: Revolutionizing the Job Search with Resume Enhancement and Tailored Recommendations

The Resume Enhancer and Job Recommendation System is designed to meet the unique challenges faced by job seekers in today's dynamic job market. Leveraging cutting-edge natural language processing (NLP) techniques, the present system provides a tailored solution to streamline the job search process. The present Resume Enhancer component utilizes advanced NLP algorithms to analyse resumes and job descriptions, generating comprehensive eligibility scores and targeted skill recommendations. This ensures that candidates' resumes are optimized to effectively showcase their qualifications and expertise to potential employers. The present Job Recommendation feature delivers personalized job listings tailored to each user's selected roles or career aspirations. The authors implemented machine learning algorithms such as the Random Forest Classifier and K-means Clustering, the system matches candidate preferences and qualifications with relevant job opportunities, increasing the likelihood of finding the perfect fit. Overall, the Resume Enhancer and Job Recommendation System serves as a valuable tool for job seekers, empowering them to navigate the complexities of the modern job market with confidence. With its user-centric approach and advanced technology, the present system enhances employability and facilitates career growth for individuals at every stage of their professional journey.

How Factually Accurate is GPT-3? A Focused Case Study on Helping Malaysia’s B40s Through e-Commerce

GPT-3 (Generative Pre-trained Transformer 3) is an advanced natural language processing model utilizing unsupervised learning to generate sophisticated human-like text. GPT-3 has been lauded for its potential to revolutionize the field of natural language processing, with its capacity to generate a variety of text with a high degree of fluency and accuracy. We examine the ability of GPT-3’s to produce text related to a focused subject matter: alleviating poverty in Malaysia through e-Commerce. We especially examine GPT-3’s ability to produce factual responses within this narrow context. It was discovered that GPT-3 could produce plausible statements, albeit some of them being factually debatable or incorrect due to how its training data was sourced. We also discuss how GPT-3 could be used unscrupulously to either produce academic-sounding responses that appear to be a product of research, but possibly untrue or inaccurate and discuss its potential ramifications (such as propaganda and disinformation). We end the paper with some suggestions to the brilliant team at OpenAI to further improve GPT-3 for the advancement of humankind.

SPEECH TO SIGN CONVERSION USING NATURAL LANGUAGE PROCESSING

Speech to sign conversion is one essential piece of technology that helps the hearing community and the hearing impaired communicate. This paper presents a novel approach utilizing Natural Language Processing (NLP) techniques for speech to sign conversion. The system that is being suggested leverages advanced NLP algorithms to transcribe spoken language into text, which is thereafter converted to sign language. The process involves several key steps: speech recognition and sign language synthesis. The synthesized sign language gestures are generated based on a comprehensive database of sign language vocabulary and grammar rules. The proposed speech to sign conversion system demonstrates promising outcomes concerning accuracy, efficiency, and usability. By harnessing the power of NLP, this technology possesses the capacity to significantly enhance communication accessibility for the hearing-impaired community, facilitating seamless interaction n a number of fields, such as education and healthcare and social communication. Key Words: Speech Recognition, Natural Language Processing, Tokenization, Lemmatization, Parsing.

Clustering asset markets based on volatility connectedness to political news

To assess similarities in international asset markets’ responses to political news, we construct a political news index using advanced natural language processing. We then examine how the volatility across international asset markets is connected to the development of our political news index by measuring the daily directional connectedness using a VAR-based framework. Finally, we apply an unsupervised algorithm to cluster markets based on their volatility connectedness to political news. Our analysis reveals eight distinct clusters that reflect the markets’ sensitivities to political dynamics. This data-driven analysis offers insights into the influence of political developments on market volatility.

ChatGPT as a Tool for Medical Education and Clinical Decision-Making on the Wards: Case Study.

Large language models (LLMs) are computational artificial intelligence systems with advanced natural language processing capabilities that have recently been popularized among health care students and educators due to their ability to provide real-time access to a vast amount of medical knowledge. The adoption of LLM technology into medical education and training has varied, and little empirical evidence exists to support its use in clinical teaching environments. The aim of the study is to identify and qualitatively evaluate potential use cases and limitations of LLM technology for real-time ward-based educational contexts. A brief, single-site exploratory evaluation of the publicly available ChatGPT-3.5 (OpenAI) was conducted by implementing the tool into the daily attending rounds of a general internal medicine inpatient service at a large urban academic medical center. ChatGPT was integrated into rounds via both structured and organic use, using the web-based "chatbot" style interface to interact with the LLM through conversational free-text and discrete queries. A qualitative approach using phenomenological inquiry was used to identify key insights related to the use of ChatGPT through analysis of ChatGPT conversation logs and associated shorthand notes from the clinical sessions. Identified use cases for ChatGPT integration included addressing medical knowledge gaps through discrete medical knowledge inquiries, building differential diagnoses and engaging dual-process thinking, challenging medical axioms, using cognitive aids to support acute care decision-making, and improving complex care management by facilitating conversations with subspecialties. Potential additional uses included engaging in difficult conversations with patients, exploring ethical challenges and general medical ethics teaching, personal continuing medical education resources, developing ward-based teaching tools, supporting and automating clinical documentation, and supporting productivity and task management. LLM biases, misinformation, ethics, and health equity were identified as areas of concern and potential limitations to clinical and training use. A code of conduct on ethical and appropriate use was also developed to guide team usage on the wards. Overall, ChatGPT offers a novel tool to enhance ward-based learning through rapid information querying, second-order content exploration, and engaged team discussion regarding generated responses. More research is needed to fully understand contexts for educational use, particularly regarding the risks and limitations of the tool in clinical settings and its impacts on trainee development.

Braille-Vox Pro Empowering Inclusive Communication

Braille-Vox Pro is an innovative project with the objective of creating a voice-to-Braille conversion system for individuals with vision impairments. The project intends to overcome the reading and writing difficulties encountered by visually impaired individuals, which can have a substantial impact on their ability to access information and communicate effectively. By turning spoken words into Braille text in real-time, the technology will give a practical answer to these issues, allowing visually impaired people to be more autonomous and productive. The research employs advanced natural language processing algorithms capable of effectively recognizing and interpreting spoken words and translating them to Braille text. Also, the system will include a Braille display device that will allow visually impaired individuals to read the transformed text. The development of this technology will give visually impaired individuals with a new degree of accessibility and inclusion, providing them more effective communication and information access. The Braille-Vox Pro project is a huge advancement in assistive technology, providing visually impaired folks with a much-needed answer to their difficulties. By allowing individuals to read and write Braille with their voice, the technology will enhance their capacity to communicate, gain access to information, and participate more fully in society. This project has the potential to aid millions of visually impaired individuals worldwide, which is a tremendous impact. The Braille-Vox Pro project is an innovative and vital Endeavor that will have a significant influence on the lives of individuals with vision impairments. [1] Keywords— Sub-images, Fuzzy logic, Image enhancement, Histogram, HSV, Image processing.

Video Summarization for Marathi Language

The Video Summarization Platform using Python Flask is a comprehensive tool designed to summarize Marathi and English videos while providing summaries in Hindi, Marathi, and English languages. Leveraging machine learning and natural language processing (NLP) techniques, this platform offers a sophisticated solution for efficiently extracting key information from videos. The platform begins by transcribing the audio content of the video into text using automatic speech recognition (ASR) technology. This transcription process ensures that the platform can accurately analyze and summarize the video's content. Next, the text is translated into the target languages, namely Hindi, Marathi, and English, enabling users from diverse linguistic backgrounds to access the summarized content. To generate concise and informative summaries, advanced NLP algorithm is applied. This algorithm analyze the transcribed text to identify the most significant phrases, sentences, and concepts. By considering factors such as keyword frequency, semantic relevance, and context, the platform effectively distils the video's content into digestible summaries. Additionally, machine learning models are employed to classify the type of video content. These models are trained on diverse datasets encompassing various video genres and topics. By recognizing patterns and features within the video content, the platform can accurately categorize videos into distinct types, such as news, interviews, tutorials, or entertainment. The platform's user interface, powered by Python Flask, offers a seamless experience for users to upload videos, select their preferred language for summarization, and receive concise summaries in their chosen languages. The intuitive design ensures accessibility and ease of use, catering to both novice and advanced users. Overall, the Video Summarization Platform serves as a valuable resource for individuals seeking efficient ways to consume multimedia content. Whether for educational, informational, or entertainment purposes, this platform empowers users to access summarized video content in multiple languages, facilitated by cutting-edge machine learning and NLP technologies. Key Words: Transcription, Marathi-speaking users, Marathi YouTube videos, video content, transcription, summary, translation, Natural Language Toolkit (NLTK), content comprehension, user interaction data, past summaries, recommendation

A micro-credential approach for life-long learning in the urban renewable energy sector

The present paper describes the development of a novel framework for the creation of specialised Micro-Credentials supporting the training and re-training of students and professionals on the integration of renewable energy and sustainable fuels in urban settings. The framework is built upon a set of stackable micro-credentials, co-designed with the stakeholders input and it uses advanced natural language processing (NLP) and machine learning algorithms to assess the impact on the job market at regional level. The use of Micro-Credentials are considered to be the optimal methodology for enhancing the knowledge of specific topics especially for life-long learning for professionals. A co-design approach of such an innovative educational framework with relevant stakeholders fosters a tailored educational path for green upskilling. Finally, the framework is validated processing and analysing a large dataset of job descriptions, extracting the skills required by the market, organising the skills in categories and clusters. All this process lead to the creation of a basket of 74 Micro-Credentials oriented to students and professional with both a technical and non-technical backgrounds.

TeenyTinyLlama: Open-source tiny language models trained in Brazilian Portuguese

Large language models (LLMs) have significantly advanced natural language processing, but their progress has yet to be equal across languages. While most LLMs are trained in high-resource languages like English, multilingual models generally underperform monolingual ones. Additionally, aspects of their multilingual foundation sometimes restrict the byproducts they produce, like computational demands and licensing regimes. In this study, we document the development of open-foundation models tailored for use in low-resource settings, their limitations, and their benefits. This is the TeenyTinyLlama pair: two compact models for Brazilian Portuguese text generation. We release them under the permissive Apache 2.0 license on GitHub and Hugging Face for community use and further development.

Leveraging mobile NER for real-time capture of symptoms, diagnoses, and treatments from clinical dialogues

In the dynamic world of healthcare technology, efficiently and accurately extracting medical data from physician-patient conversations is vital. This paper presents a new approach in healthcare technology, employing Natural Language Processing (NLP) to identify and extract critical information from doctor-patient conversations on mobile devices. Unlike traditional methods that rely on Electronic Health Records, our novel application enables the extraction of symptoms, diagnoses, and treatments directly on a mobile device during medical consultations, significantly enhancing patient privacy. We managed to integrate both Bidirectional Encoder Representations from Transformers (BERT) models and optimized Large Language Models (LLMs) on a mobile device without compromising performance significantly. Our findings reveal that the BERT model attained an F1-score of 85.1%, while FLERT and its compressed variant DistilFLERT showed superior performance. The FLAN-T5 model outperformed all models we tested with scores up to 92.7%. These results highlight the efficacy of leveraging advanced NLP and LLM technologies in healthcare environments on a mobile device, offering a promising direction for accessible and efficient patient care.

TalkTrek: Journeying Through the Terrain of Text-based Speech Synthesis

Abstract: This research paper delves into the development and evaluation of TextTalker, an innovative voice-enabled education chatbot designed to enhance learning experiences. TextTalker integrates advanced natural language processing capabilities with voice recognition technology to facilitate seamless interactions between users and educational content. Furthermore, it incorporates a unique feature allowing users to access relevant YouTube videos directly within the chat interface, fostering a multi-modal learning environment. The system's architecture and design are meticulously crafted to ensure user engagement, accessibility, and effectiveness in delivering educational materials. Through a series of usability studies and user feedback analysis, this research evaluates the efficacy of TextTalker in supporting learning objectives and enhancing user satisfaction. The findings reveal promising results, indicating high levels of user engagement and satisfaction with the platform's intuitive interface and diverse learning resources. Moreover, incorporating feedback mechanisms empowers users to contribute to the refinement and enhancement of TextTalker's functionalities, fostering a collaborative learning ecosystem. Overall, TextTalker represents a significant advancement in educational technology, offering a user-centric approach to interactive learning through voice-enabled chatbots integrated with multimedia content delivery and feedback mechanisms

Cross-Platform Bug Localization Strategies: Utilizing Machine Learning for Diverse Software Environment Adaptability

This paper introduces a novel hybrid machine learning model that combines Long Short-Term Memory (LSTM) networks and SHapley Additive exPlanations (SHAP) to enhance bug localization across multiple software platforms. The aim is to adapt to the variability inherent in different operating systems and provide transparent, interpretable results for software developers. Our methodology includes comprehensive preprocessing of bug report data using advanced natural language processing techniques, followed by feature extraction through word embeddings to accommodate the sequential nature of text data. The LSTM model is trained and evaluated on a dataset of simulated bug reports, with the results interpreted using SHAP values to ensure clarity in decision-making. The results demonstrate the model’s robustness, adaptability, and consistent performance across platforms, as evidenced by accuracy, precision, recall, and F1 scores. The dataset's distribution of bug categories and statuses further provides valuable insights into common software development issues.

Unlocking Digital Gates: The Essence of Website Authentication Using Natural Language Processing

Abstract: In the rapidly evolving landscape of cyberspace, ensuring the security and reliability of websites has become increasingly critical. Traditional methods of website validation often fall short in accurately identifying vulnerabilities and determining the active status of websites, leading to potentialrisks for users and organizations. To address these challenges, this paper presents a comprehensive approach to website vali- dation leveraging advanced Natural Language Processing (NLP) techniques. By harnessing the power of NLP, our methodology aims to significantly enhance web security and user experience byeffectively identifying vulnerabilities and determining the active status of websites. The proposed methodology comprises two key components: vulnerability detection and active status determination. In the vulnerability detection phase, our system utilizes NLP algorithmsto analyze website content and metadata, enabling the identifi- cation of potential security risks

Advanced Social Media Toxic Comments Detection System Using AI

Abstract: In the contemporary digital landscape, social media platforms have evolved into essential components of our daily lives, fostering connections, idea sharing, and meaningful conversations. Nevertheless, the escalating volume of online interactions has ushered in a concerning rise in toxic comments and cyberbullying, casting a shadow over the potential for a healthy onlineenvironment. Toxic comments, spanning hate speech, harassment, and offensive content, not only inflict harm on individuals but also detrimentally affect the overall user experience. This project seeks to address this pressing issue through the development of a cutting-edge Toxic Comment Detection system, leveraging the power of Natural Language Processing (NLP) and Machine Learning (ML) techniques. The primary objective of this endeavor is to create an automated system capable of identifying and flagging toxic comments in realtime across various social media platforms. By employing advanced NLP algorithms and ML models, the system aims to analyze textual content swiftly and accurately, pinpointing instances of toxicity. Once identified, the system will promptly notify moderators, enabling swift intervention and potential removal of the harmful content. By implementing this technological solution, the project aspires to contribute significantly to fostering a safer and more inclusive online environment where users can engage without fear of encountering toxic behavior. Through the fusion of NLP and ML, this endeavor aims to exemplify the transformative potential of technology in mitigating the challenges posed by toxic comments in the digital age.

Construction of Algorithm for English Learners to Read Foreign Literature Based on Machine Translation Technology

This study focuses on the development of an algorithm aimed at assisting English learners in comprehending foreign literature through the utilization of machine translation technology. With the growing importance of multilingual proficiency in a globalized world, the ability to read and understand literature in foreign languages is increasingly valued. However, language barriers often hinder learners' comprehension and appreciation of such texts. To address this challenge, our research endeavors to construct an algorithm that leverages machine translation techniques to facilitate the reading process for English learners. By integrating advanced translation algorithms and natural language processing methods, the proposed system aims to provide accurate and contextually relevant translations of foreign literature into English. Additionally, the algorithm will incorporate features tailored to the needs of English learners, such as vocabulary assistance, grammatical explanations, and cultural context annotations, to enhance their reading experience and comprehension levels. Through rigorous experimentation and evaluation, the effectiveness and usability of the algorithm will be assessed, with the ultimate goal of empowering English learners to engage more deeply with foreign literature and broaden their linguistic and cultural horizons.