Natural Language Patterns Research Articles

A Research Paper on: AI/ML-Based Data Duplication Alert System

Data duplication is a pervasive issue across organizations dealing with extensive data, leading to wasted storage, increased processing costs, and compromised data integrity. Traditional methods for identifying and managing data duplication are often time-consuming and inefficient, especially as data volumes continue to scale. To address these challenges, we propose an AI/ML-Based Data Duplication Alert System, leveraging machine learning algorithms to intelligently detect and alert users to potential data duplication. The system employs advanced techniques such as natural language processing (NLP), pattern recognition, and clustering to analyze data structures and content across databases, documents, and storage locations. By utilizing both supervised and unsupervised learning models, it can detect duplicate data entries even when they include typos or structural variations. Models are evaluated using statistical metrics such as Receiver Operating Characteristic (ROC) curves, precision, recall, and accuracy rates exceeding 95%, ensuring high reliability in detecting duplicates. In addition to real-time alerts, the system integrates seamlessly with data management workflows, preventing duplicate entries at the point of data entry, thus upholding data quality standards. This AI/ML-based solution automates the detection process, enabling faster response times, reducing storage requirements, and improving data accuracy. By ensuring data consistency, the system promotes more efficient data utilization across organizational systems while maintaining a high standard of accuracy and precision.

Variational Autoencoders-Based Algorithm for Multi-Criteria Recommendation Systems

In recent years, recommender systems have become a crucial tool, assisting users in discovering and engaging with valuable information and services. Multi-criteria recommender systems have demonstrated significant value in assisting users to identify the most relevant items by considering various aspects of user experiences. Deep learning (DL) models demonstrated outstanding performance across different domains: computer vision, natural language processing, image analysis, pattern recognition, and recommender systems. In this study, we introduce a deep learning model using VAE to improve multi-criteria recommendation systems. Specifically, we propose a variational autoencoder-based model for multi-criteria recommendation systems (VAE-MCRS). The VAE-MCRS model is sequentially trained across multiple criteria to uncover patterns that allow for better representation of user–item interactions. The VAE-MCRS model utilizes the latent features generated by the VAE in conjunction with user–item interactions to enhance recommendation accuracy and predict ratings for unrated items. Experiments carried out using the Yahoo! Movies multi-criteria dataset demonstrate that the proposed model surpasses other state-of-the-art recommendation algorithms, achieving a Mean Absolute Error (MAE) of 0.6038 and a Root Mean Squared Error (RMSE) of 0.7085, demonstrating its superior performance in providing more precise recommendations for multi-criteria recommendation tasks.

Exploring How Education Can Leverage Artificial Intelligence for Social Good

Artificial intelligence (AI) is rapidly transforming society and industries, presenting both opportunities and ethical challenges. AI enables machines to perform tasks traditionally done by humans, such as natural language processing, pattern recognition, decision-making, and problem-solving (Brookings, 2023). In education, AI enhances teaching methodologies, student assessment, and administrative tasks through tools like intelligent tutoring systems, adaptive learning platforms, and educational chatbots. These tools offer customised learning experiences, immediate feedback, and data-driven insights. This research aims to investigate how AI can be leveraged within education to promote social good by identifying how familiar educators and students are with AI tools, identify how educators and students perceive the role of AI in education and what are the current applications of AI technologies in educational settings and how widely are they used. Finally, discuss the opportunities and ethical considerations of integrating AI in education. AI technologies can address critical social challenges such as inequality, accessibility, and personalised learning. According to Luckin et al. (2016), "AI can provide tailored educational experiences that adapt to individual learning needs, thus promoting equity in education." This exploratory research begins with an overview of AI's role and tools in education, followed by a discussion of the challenges, opportunities, and ethical considerations associated with AI integration. Understandings are drawn from educator’s response to a questionnaire and a focus group with first year and final-year third level students. This qualitative data, analysed using NVivo software, reveals key themes and significant findings on effectively utilising AI in education.

Machine Learning Approach for Arabic Handwritten Recognition

Text recognition is an important area of the pattern recognition field. Natural language processing (NLP) and pattern recognition have been utilized efficiently in script recognition. Much research has been conducted on handwritten script recognition. However, the research on the Arabic language for handwritten text recognition received little attention compared with other languages. Therefore, it is crucial to develop a new model that can recognize Arabic handwritten text. Most of the existing models used to acknowledge Arabic text are based on traditional machine learning techniques. Therefore, we implemented a new model using deep machine learning techniques by integrating two deep neural networks. In the new model, the architecture of the Residual Network (ResNet) model is used to extract features from raw images. Then, the Bidirectional Long Short-Term Memory (BiLSTM) and connectionist temporal classification (CTC) are used for sequence modeling. Our system improved the recognition rate of Arabic handwritten text compared to other models of a similar type with a character error rate of 13.2% and word error rate of 27.31%. In conclusion, the domain of Arabic handwritten recognition is advancing swiftly with the use of sophisticated deep learning methods.

Leveraging ChatGPT to Enhance Debugging: Evaluating AI-Driven Solutions in Software Development

Debugging is a crucial component of software development, focusing on identifying and correcting problems, commonly known as bugs, in code. Recent advances in artificial intelligence (AI) have introduced new opportunities for automating this process using language models such as ChatGPT. This article explores the use of ChatGPT in addressing programming challenges, assessing its ability to detect, anticipate, and rectify errors in code. The research examines ChatGPT’s debugging capabilities by evaluating its natural language processing, knowledge representation, and pattern recognition skills. The text compares ChatGPT’s performance with conventional debugging tools through real-world examples and case studies. The findings suggest that ChatGPT can effectively assist in debugging by automatically identifying and correcting errors, predicting issues early in the development phase, and clarifying the underlying causes of bugs. However, the system’s effectiveness depends on the quality of its training data and architecture. While ChatGPT has the potential to be a valuable tool in the debugging process, it is essential to combine it with traditional debugging methods to ensure accuracy and reliability. Further research is needed to enhance ChatGPT’s capabilities and evaluate its effectiveness in real-world scenarios.

Towards Enhanced Security: An improved approach to Phishing Email Detection

Email phishing assaults remain a widespread catastrophe to individuals and businesses, using human weaknesses to obtain unauthorised access to sensitive information. This research study presents an upgraded email phishing detection system that uses machine learning approaches. To construct a robust and adaptable model, the system includes a complete feature set such as email content analysis, sender reputation, and behavioural patterns. The one that has been proposed uses a new combination of supervised and unsupervised machine learning algorithms to analyse email properties and user behaviour, allowing for the detection of subtle phishing signs. The term of body content analysis, URL analysis, and QR code information are among the features retrieved and analysed utilising advanced natural language processing and pattern recognition algorithms. Novelty lies in the integration of supervised and unsupervised machine learning algorithms to identify subtle phishing indicators, along with advanced natural language processing and pattern recognition algorithms for analyzing email properties. A benchmark dataset is used for the proposed system's validation, and a comparison with other phishing detection techniques shows improved, lower false-positive rates. The results indicate the system's ability to effectively discern phishing emails while minimizing the impact on legitimate communication. The system demonstrates a notable improvement by including a diverse range of features and state-of-the-art machine learning algorithms, which makes it a valuable asset to the cybersecurity toolkit for safeguarding email correspondence.

GPT understands, too

Prompting a pretrained language model with natural language patterns has been proved effective for natural language understanding (NLU). However, our preliminary study reveals that manual discrete prompts often lead to unstable performance—e.g., changing a single word in the prompt might result in substantial performance drop. We propose a novel method P-Tuning that employs trainable continuous prompt embeddings in concatenation with discrete prompts. Empirically, P-Tuning not only stabilizes training by minimizing the gap between various discrete prompts, but also improves performance by a sizeable margin on a wide range of NLU tasks including LAMA and SuperGLUE. P-Tuning is generally effective for both frozen and tuned language models, under both the fully-supervised and few-shot settings.

A developmental account of the role of sequential dependencies in typical and atypical language learners

ABSTRACT The Gerken lab has shown that infants are able to learn sound patterns that obligate local sequential dependencies that are no longer readily accessible to adults. The Goffman lab has shown that children with developmental language disorder (DLD) exhibit deficits in learning sequential dependencies that influence the acquisition of words and grammar, as well as other types of domain general sequences. Thus, DLD appears to be an impaired ability to detect and deploy sequential dependencies over multiple domains. We meld these two lines of research to propose a novel account in which sequential dependency learning is required for many phonological and morphosyntactic patterns in natural language and is also central to the language and domain general deficits that are attested in DLD. However, patterns that are not dependent on sequential dependencies but rather on networks of stored forms are learnable by children with DLD as well as by adults.

Noun Sequence Statistics Affect Serial Recall and Order Recognition Memory.

Most theories of verbal working memory recognize that language comprehension and production processes play a role in word memory for familiar sequences, but not for novel lists of nouns. Some language emergent theories propose that language processes can support verbal working memory even for novel sequences. Through corpus analyses, we identify sequences of two nouns that resemble patterns in natural language, even though the sequences are novel. We present 2 experiments demonstrating better recall in college students for these novel sequences over the same words in reverse order. In a third experiment, we demonstrate better recognition of the order of these sequences over a longer time scale. These results suggest verbal working memory and recognition of order over a delay are influenced by language knowledge processes, even for novel memoranda that approximate noun lists typically employed in memory experiments.

Use It or Lose It Harmony in Komo

This paper discusses a case of putative dominance reversal in the Komo language (Otero 2015, 2019), which we analyze as a related, but distinct repair strategy called “Use it or Lose it” (Mullin & Pater 2015).Mullin & Pater (2015) argue that Use it or Lose it harmony is a pathological prediction of Agree for the same basic reason that “Sour Grapes” harmony (Wilson 2003, 2006; Heinz & Lai 2013) has been regarded as pathological – both Use it or Lose it and Sour Grapes harmony patterns are non-myopic (Wilson 2003, 2006). Wilson argues that unbounded spreading patterns are universally myopic, and as such, no theory should predict that the realization of some element in spreading – trigger or target – depends on downstream information. However, recent research has shown that some patterns in natural languages are, in fact, non-myopic, indicating that the predictions of Agree are not as problematic as previously thought. This paper argues that the best analysis of Komo relies on the activity of [Atr] and both regressive [+Atr] spreading and [+Atr] trigger effacement are repairs to a single marked structure in the language, *VC0[Hi, Atr].

An Optimised Defensive Technique to Recognize Adversarial Iris Images Using Curvelet Transform

Deep Learning is one of the most popular computer science techniques, with applications in natural language processing, image processing, pattern identification, and various other fields. Despite the success of these deep learning algorithms in multiple scenarios, such as spam detection, malware detection, object detection and tracking, face recognition, and automatic driving, these algorithms and their associated training data are rather vulnerable to numerous security threats. These threats ultimately result in significant performance degradation. Moreover, the supervised based learning models are affected by manipulated data known as adversarial examples, which are images with a particular level of noise that is invisible to humans. Adversarial inputs are introduced to purposefully confuse a neural network, restricting its use in sensitive application areas such as biometrics applications. In this paper, an optimized defending approach is proposed to recognize the adversarial iris examples efficiently. The Curvelet Transform Denoising method is used in this defense strategy, which examines every sub-band of the adversarial images and reproduces the image that has been changed by the attacker. The salient iris features are retrieved from the reconstructed iris image by using a pre-trained Convolutional Neural Network model (VGG 16) followed by Multiclass classification. The classification is performed by using Support Vector Machine (SVM) which uses Particle Swarm Optimization method (PSO-SVM). The proposed system is tested when classifying the adversarial iris images affected by various adversarial attacks such as FGSM, iGSM, and Deepfool methods. An experimental result on benchmark iris dataset, namely IITD, produces excellent outcomes with the highest accuracy of 95.8% on average.

Approximating functions with multi-features by deep convolutional neural networks

Deep convolutional neural networks (DCNNs) have achieved great empirical success in many fields such as natural language processing, computer vision, and pattern recognition. But there still lacks theoretical understanding of the flexibility and adaptivity of DCNNs in various learning tasks, and the power of DCNNs at feature extraction. We propose a generic DCNN structure consisting of two groups of convolutional layers associated with two downsampling operators, and a fully connected layer, which is determined only by three structural parameters. Our generic DCNNs are capable of extracting various features including not only polynomial features but also general smooth features. We also show that the curse of dimensionality can be circumvented by our DCNNs for target functions of the compositional form with (symmetric) polynomial features, spatially sparse smooth features, and interaction features. These demonstrate the expressive power of our DCNN structure, while the model selection can be relaxed comparing with other deep neural networks since there are only three hyperparameters controlling the architecture to tune.

Typist Experiment: an Investigation of Human-to-Human Dictation via Role-play to Inform Voice-based Text Authoring

Voice dictation is increasingly used for text entry, especially in mobile scenarios. However, the speech-based experience gets disrupted when users must go back to a screen and keyboard to review and edit the text. While existing dictation systems focus on improving transcription and error correction, little is known about how to support speech input for the entire text creation process, including composition, reviewing and editing. We conducted an experiment in which ten pairs of participants took on the roles of authors and typists to work on a text authoring task. By analysing the natural language patterns of both authors and typists, we identified new challenges and opportunities for the design of future dictation interfaces, including the ambiguity of human dictation, the differences between audio-only and with screen, and various passive and active assistance that can potentially be provided by future systems.

Twitter Big Data as a Resource for Exoskeleton Research: A Large-Scale Dataset of about 140,000 Tweets from 2017–2022 and 100 Research Questions

The exoskeleton technology has been rapidly advancing in the recent past due to its multitude of applications and diverse use cases in assisted living, military, healthcare, firefighting, and industry 4.0. The exoskeleton market is projected to increase by multiple times its current value within the next two years. Therefore, it is crucial to study the degree and trends of user interest, views, opinions, perspectives, attitudes, acceptance, feedback, engagement, buying behavior, and satisfaction, towards exoskeletons, for which the availability of Big Data of conversations about exoskeletons is necessary. The Internet of Everything style of today’s living, characterized by people spending more time on the internet than ever before, with a specific focus on social media platforms, holds the potential for the development of such a dataset by the mining of relevant social media conversations. Twitter, one such social media platform, is highly popular amongst all age groups, where the topics found in the conversation paradigms include emerging technologies such as exoskeletons. To address this research challenge, this work makes two scientific contributions to this field. First, it presents an open-access dataset of about 140,000 Tweets about exoskeletons that were posted in a 5-year period from 21 May 2017 to 21 May 2022. Second, based on a comprehensive review of the recent works in the fields of Big Data, Natural Language Processing, Information Retrieval, Data Mining, Pattern Recognition, and Artificial Intelligence that may be applied to relevant Twitter data for advancing research, innovation, and discovery in the field of exoskeleton research, a total of 100 Research Questions are presented for researchers to study, analyze, evaluate, ideate, and investigate based on this dataset.

From computer vision to short text understanding: Applying similar approaches into different disciplines

With the development of IoT and 5G technologies, more and more online resources are presented in trendy multimodal data forms over the Internet. Hence, effectively processing multimodal information is significant to the development of various online applications, including e-Iearning and digital health, to just name a few. However, most AI-driven systems or models can only handle limited forms of information. In this study, we investigate the correlation between natural language processing (NLP) and pattern recognition, trying to apply the mainstream approaches and models used in the computer vision (CV) to the task of NLP. Based on two different Twitter datasets, we propose a convolutional neural network based model to interpret the content of short text with different goals and application backgrounds. The experiments have demonstrated that our proposed model shows fairly competitive performance compared to the mainstream recurrent neural network based NLP models such as bidirectional long short-term memory (Bi-LSTM) and bidirectional gate recurrent unit (Bi-GRU). Moreover, the experimental results also demonstrate that the proposed model can precisely locate the key information in the given text.

SAMPURNA- A Multi-Functional Medical Assistant Application Framework

Abstract: In recent times, the need for the advancement of medical facilities has been majorly realised and a lot of efforts have been made in the same direction. Healthcare is vital to leading a healthy and prosperous life. However, there are still certain arenas where there is a need for improvement so that people can benefit the most. The COVID-19 pandemic made everyone realise that there is nothing more important than their own health and family. During the peak times when India was trembling with the COVID waves, in spite of the ceaseless efforts from the doctors, there were still many people who remained unattended and eventually perished because of the lack of awareness and aid facilities. Had there been a system through which they could have gotten the aid on time, they wouldn’t have died a helpless death. Here we bring a system which has the capability of solving such issues for one and all. This Multi-Functional Medical Assistant Framework, as the name suggests, would provide the patient or the person in need with medical aid. The Chatbot will provide the exact medical composition that would suite their metabolism in an orchestrated and expedited manner. In this paper we have provided the design, the internal functioning, and the implementation of our application. General Terms Natural Processing Language Pattern Matching Artificial Intelligence Medicine. Keywords: Chatbots, Health, Bots, Natural Language, Covid-19

Recent advances in language & knowledge engineering

Language & Knowledge Engineering is essential for the successfully development of artificial intelligence. The technologies proposed in international forums are meant to improve all areas of our daily life whether it is related to production industries, social communities, government, education, or something else. We consider very important to reveal the recent advances Intelligent and Fuzzy Systems applied to Language & Knowledge Engineering because they are the base for the society of tomorrow. Thus, the aim of this special issue of Journal of Intelligent and Fuzzy Systems is to present a collection of papers that cover recent research results on the two wide topics: language and knowledge engineering. Even if the special issue is structured into these two general topics, we have covered specific themes such as the following ones: Natural Language Processing, Knowledge engineering, Pattern recognition, Artificial Intelligence and Language, Information Processing, Machine Learning Applied to Text Processing, Image and Text Classification, Multimodal data analysis, sentiment analysis, etc.

Application of Artificial Intelligence on Library System, Operations and Services

This paper is going to aware in the field of Artificial Intelligence focusing on how it’s applied in the Library world. The concept such as machine learning, deep learning and their various applications by Technique is enumerated. In this paper an attempt has been made to identify the different applications of Artificial Intelligence into the libraries. The various concepts such as expert system, natural language processing, pattern recognition and robotics and their application to the library operation and services have been explained thoroughly. The advantages and disadvantages of Artificial Intelligence have also been discussed.

Aspect construal in Mandarin: a usage-based constructionist perspective onLE

AbstractDespite extensive research efforts to explain the Mandarin Chinese particlele, confusion persists in the absence of a unitary theory and sufficient empirical evidence. This study provides a unitary account ofleby adopting a usage-based constructionist approach, one that liberates grammatical aspect from, and is able to accommodate, lexical aspect. We argue thatleparticipates in two distinct family resemblance constructions of aspect construal associated with two distinct sentential positions. The clause-internalleconstruction construes the closing or final boundary of an event and the clause-finalleconstruction construes the opening or initial boundary of an event. Corpus analysis showed that the two aspect constructions have distinct patterns in natural language uses that are consistent with the proposed construals. Results from elicited response data showed that native speakers paid attention to construction-level formal and semantic cues in making family resemblance judgments about tokens of the two constructions. This study has both theoretical and methodological implications for crosslinguistic research on grammatical aspect in relation to lexical aspect and for usage-based constructionist approaches to grammatical categories beyond aspect.

Applications of artificial intelligence systems

Nowadays artificial intelligence is a rapidly developing technology that encompasses the development of intelligent algorithms and machines capable of learning. Therefore, it is relevant and timely to examine the topic. These artificial intelligence algorithms and machines have the ability to perform tasks that traditionally relied on human intelligence in the past. This study provides an in-depth exploration of artificial intelligence systems and their key components. It examines various aspects of artificial intelligence systems, including natural language processing, machine learning, detection and pattern recognition, and knowledge representation and other form of artificial intelligence systems. Natural language processing enables machines to understand and generate human language, while machine learning empowers systems to learn from data and improve their performance over time. Detection and pattern recognition allow artificial intelligence systems to interpret and understand complex sensory inputs, while knowledge representation enables the storage and utilization of information. Furthermore, other form of artificial intelligence systems will be also discussed. This study sheds light on the fundamental elements of artificial intelligence systems, paving the way for their practical applications and advancements.