Digital Commons Network^™

Studying Memes During Covid Lockdown As A Lens Through Which To Understand Video-Mediated Communication Interactions, Tatyana Claytor

Electronic Theses and Dissertations, 2020-2023

The purpose of this study is to analyze image macros about video-mediated communication (VMC) created during the time frame of 2020-2021 when people all over the world started using Zoom and VMC for work and school. It is a unique opportunity to study how users' interactions with themselves and with others were affected at a time when a lot of people started using the technology at the same time. Because the focus is on interactions, I narrowed it down to three topics to analyze the memes: presence, self, and space and place to analyze the memes. I chose memes relating …

Ocr Post-Processing Using Large Language Models, Mahdi Hajiali

UNLV Theses, Dissertations, Professional Papers, and Capstones

Optical Character Recognition (OCR) technology transforms textual visuals into an electronically readable, non-graphical format of the text. This allows the editing and other text manipulation of the content by language technology software such as machine translation, text comprehension, query-answering systems, and search engines. While Optical Character Recognition (OCR) systems continually progress towards greater precision, several complications persist when dealing with low-resolution source images or those with multicolored backgrounds. Consequently, the text derived from OCR necessitates additional refinement to optimize accuracy, beneficial for various subsequent applications. It is recognized that the character accuracy of OCR-generated text may influence certain natural language …

S2cd: Self-Heuristic Speaker Content Disentanglement For Any-To-Any Voice Conversion, Pengfei Wei, Xiang Yin, Chunfeng Wang, Zhonghao Li, Xinghua Qu, Zhiqiang Xu, Zejun Ma

Machine Learning Faculty Publications

In this paper, we propose a Self-heuristic Speaker Content Disentanglement (S2CD) model for any to any voice conversion without using any external resources, e.g., speaker labels or vectors, linguistic models, and transcriptions. S2CD is built on the disentanglement sequential variational autoencoder (DSVAE), but improves DSVAE structure at the model architecture level from three perspectives. Specifically, we develop different structures for speaker and content encoders based on their underlying static/dynamic property. We further propose a generative graph, modelled by S2CD, so as to make S2CD well mimic the multi-speaker speech generation process. Finally, we propose a self-heuristic way to introduce bias …

Fooctts: Generating Arabic Speech With Acoustic Environment For Football Commentator, Massa Baali, Ahmed Ali

Machine Learning Faculty Publications

This paper presents FOOCTTS, an automatic pipeline for a football commentator that generates speech with background crowd noise. The application gets the text from the user, applies text pre-processing such as vowelization, followed by the commentator's speech synthesizer. Our pipeline included Arabic automatic speech recognition for data labeling, CTC segmentation, transcription vowelization to match speech, and fine-tuning the TTS. Our system is capable of generating speech with its acoustic environment within limited 15 minutes of football commentator recording. Our prototype is generalizable and can be easily applied to different domains and languages.

Controllable Language Generation Using Deep Learning, Rohola Zandie

Electronic Theses and Dissertations

The advent of deep neural networks has sparked a revolution in Artificial Intelligence (AI), notably with the creation of Transformer models like GPT-X and ChatGPT. These models have surpassed previous methods in various Natural Language Processing (NLP) tasks. As the NLP field evolves, there is a need to further understand and question the capabilities of these models. Text generation, a crucial part of NLP, remains an area where our comprehension is limited while being critical in research.

This dissertation focuses on the challenging problem of controlling the general behaviors of language models such as sentiment, topical focus, and logical reasoning. …

Data Is The New Gold: A Singapore Perspective On The Duty Of Care Concerning A Dataset’S Role In Contributing To Bias And Ai Hallucinations, Daniel Seah

Research Collection College of Integrative Studies

Amidst the trends and advances in Artificial Intelligence (AI) techniques, the dataset’s key role in creating AI harms is a constant. Yet the literature’s attention is typically focussed on the machinelearning’s role, from which the dataset’s role is examined usually in terms of its potential for bias. Datasets also contribute to AI hallucinations. Again, the literature focuses on the composite roles of datasets and AI models in hallucinations, in isolation from a dataset’s contributory role in creating bias. Therefore, the overlapping and distinctive roles of datasets, as a dual contributor, are understudied in the literature. Through the legal concept of …

Knowledge Representation For Conceptual, Motivational, And Affective Processes In Natural Language Communication, Seng Beng Ho, Zhaoxia Wang, Boon-Kiat Quek, Erik Cambria

Research Collection School Of Computing and Information Systems

Natural language communication is an intricate and complex process. The speaker usually begins with an intention and motivation of what is to be communicated, and what outcomes are expected from the communication, while taking into consideration the listener’s mental model to concoct an appropriate sentence. Likewise, the listener has to interpret the speaker’s message, and respond accordingly, also with the speaker’s mental model in mind. Doing this successfully entails the appropriate representation of the conceptual, motivational, and affective processes that underlie language generation and understanding. Whereas big-data approaches in language processing (such as chatbots and machine translation) have performed well, …

Towards Multi-Modal Explainable Video Understanding, Kashu Yamazaki

Graduate Theses and Dissertations

This thesis presents a novel approach to video understanding by emulating human perceptual processes and creating an explainable and coherent storytelling representation of video content. Central to this approach is the development of a Visual-Linguistic (VL) feature for an interpretable video representation and the creation of a Transformer-in-Transformer (TinT) decoder for modeling intra- and inter-event coherence in a video. Drawing inspiration from the way humans comprehend scenes by breaking them down into visual and non-visual components, the proposed VL feature models a scene through three distinct modalities. These include: (i) a global visual environment, providing a broad contextual understanding of …

Transformer Reinforcement Learning Approach To Attack Automatic Fake News Detectors, Chandler Underwood

Boise State University Theses and Dissertations

Misinformation and disinformation disguised in the form of fake news stories have garnered a lot of attention as of late largely because they confuse and often anger the public, leading to a less cohesive society for us all. In response to the ever-growing issue of fake news stories circulating on social media, researchers have crafted various solutions to predict the veracity of stories in hopes of catching illegitimate ones before they can spread. In response to this research area, a newer research area focused on attacking fake news detectors is forming. In this work we have built an adversarial text …

Increasing The Efficiency And Accuracy Of Collective Intelligence Methods For Image Classification, Md Mahmudulla Hassan

Open Access Theses & Dissertations

Collective intelligence has emerged as a powerful methodology for annotating and classifying challenging data that pose difficulties for automated classifiers. It works by leveraging the concept of "wisdom of the crowds" which approximates a ground truth after aggregating experts' feedback and filtering out noise. However, challenges arise when certain applications, such as medical image classification, security threat detection, and financial fraud detection, demand accurate and reliable data annotation. The unreliability of experts due to inconsistent expertise and competencies, coupled with the associated cost and time-consuming judgment extraction, presents additional challenges.

Input aggregation is the process of consolidating and combining multiple …

Decoding The Underlying Meaning Of Multimodal Hateful Memes, Ming Shan Hee, Wen Haw Chong, Roy Ka-Wei Lee

Research Collection School Of Computing and Information Systems

Recent studies have proposed models that yielded promising performance for the hateful meme classification task. Nevertheless, these proposed models do not generate interpretable explanations that uncover the underlying meaning and support the classification output. A major reason for the lack of explainable hateful meme methods is the absence of a hateful meme dataset that contains ground truth explanations for benchmarking or training. Intuitively, having such explanations can educate and assist content moderators in interpreting and removing flagged hateful memes. This paper address this research gap by introducing Hateful meme with Reasons Dataset (HatReD), which is a new multimodal hateful meme …

Hyperbolic Graph Topic Modeling Network With Continuously Updated Topic Tree, Ce Zhang, Rex Ying, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Connectivity across documents often exhibits a hierarchical network structure. Hyperbolic Graph Neural Networks (HGNNs) have shown promise in preserving network hierarchy. However, they do not model the notion of topics, thus document representations lack semantic interpretability. On the other hand, a corpus of documents usually has high variability in degrees of topic specificity. For example, some documents contain general content (e.g., sports), while others focus on specific themes (e.g., basketball and swimming). Topic models indeed model latent topics for semantic interpretability, but most assume a flat topic structure and ignore such semantic hierarchy. Given these two challenges, we propose a …

Corporate Trade War Uncertainty And Patent Bubble, Xu Yang, Nan Hu, Peng Liang

Research Collection School Of Computing and Information Systems

This paper draws upon resource dependence theory and investigates how trade policy uncertainty affects firm strategic innovation management in China. Adopting a machine learning approach called Word2Vec from computational linguistics, we construct and validate a measure of firm-level managers’ perceived trade war uncertainty (TWU). We find that TWU has a positive effect on the number of total patent applications, but this positive effect is totally driven by low-quality patents instead of high-quality patents. Moreover, we document that firms have stronger incentives for such strategic innovation behavior when the underlying firms are more financially constrained, and/or when the management is more …

Comparative Study Of Clustering Techniques On Eye-Tracking In Dynamic 3d Virtual Environments, Scott Johnson

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Eye-tracking has been used for decades to understand how and why an individual focuses on particular objects, areas, and elements of space. A vast body of knowledge exists on how eye-tracking is measured. However, historically, eye-tracking has been predominately studied using 2D environments, with limited work in 3D environments. The purpose of this study is to identify which methods most accurately represent the areas that have captured the participant’s visual attention within a 3D dynamic environment. This will be completed by evaluating different clustering methods of fixations using a customized virtual reality tool that collects eye-tracking data. There exist several …

Numgpt: Improving Numeracy Ability Of Generative Pre-Trained Models, Zhihua Jin, Xin Jiang, Xiangbo Wang, Qun Liu, Yong Wang, Xiaozhe Ren, Huamin Qu

Research Collection School Of Computing and Information Systems

Existing generative pre-trained language models (e.g., GPT) focus on modeling the language structure and semantics of general texts. However, those models do not consider the numerical properties of numbers and cannot perform robustly on numerical reasoning tasks (e.g., math word problems and measurement estimation). In this paper, we propose NumGPT, a generative pre-trained model that explicitly models the numerical properties of numbers in texts. Specifically, it leverages a prototype-based numeral embedding to encode the mantissa of the number and an individual embedding to encode the exponent of the number. A numeral-aware loss function is designed to integrate numerals into the …

A Method For Generating A Non-Manual Feature Model For Sign Language Processing, Robert G. Smith Dr, Markus Hofmann Dr

Articles

While recent approaches to sign language processing have shifted to the domain of Machine Learning (ML), the treatment of Non-Manual Features (NMFs) remains an open question. The principal challenge facing this method is the comparatively small sign language corpora available for training machine learning models. This study produces a statistical model which may be used in future ML, rules-based, and hybrid-learning approaches for sign language processing tasks. In doing so, this research explores the emerging patterns of non-manual articulation concerning grammatical classes in Irish Sign Language (ISL). The experimental method applied here is a novel implementation of an association rules …

Transferable Curricula Through Difficulty Conditioned Generators, Sidney Tio, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Advancements in reinforcement learning (RL) have demonstrated superhuman performance in complex tasks such as Starcraft, Go, Chess etc. However, knowledge transfer from Artificial "Experts" to humans remain a significant challenge. A promising avenue for such transfer would be the use of curricula. Recent methods in curricula generation focuses on training RL agents efficiently, yet such methods rely on surrogate measures to track student progress, and are not suited for training robots in the real world (or more ambitiously humans). In this paper, we introduce a method named Parameterized Environment Response Model (PERM) that shows promising results in training RL agents …

Ai For Connectivism Learning: Undergraduate Students’ Experiences Of Chatgpt In Advanced Programming Courses, Swapna Gottipati, Kyong Jin Shim, Venky Shankararaman

Research Collection School Of Computing and Information Systems

Advanced programming skills are required for computing courses on merging topics, and students often struggle to develop these skills to solve complex problems. To address this challenge, faculty members provide additional lectures, practice sessions, and educational technology tools. This paper discusses the challenges faced by computer science students in developing advanced programming skills and explores the use of AI chatbots, specifically ChatGPT, as a support tool for learning. We study the engagement and effectiveness of ChatGPT in helping students learn advanced programming skills using two engagement learning frameworks (CIE and MELT) for evaluation. The study involves designing a computing lab …

Context-Aware Event Forecasting Via Graph Disentanglement, Yunshan Ma, Chenchen Ye, Zijian Wu, Xiang Wang, Yixin Cao, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Event forecasting has been a demanding and challenging task throughout the entire human history. It plays a pivotal role in crisis alarming and disaster prevention in various aspects of the whole society. The task of event forecasting aims to model the relational and temporal patterns based on historical events and makes forecasting to what will happen in the future. Most existing studies on event forecasting formulate it as a problem of link prediction on temporal event graphs. However, such pure structured formulation suffers from two main limitations: 1) most events fall into general and high-level types in the event ontology, …

Mastering Stock Markets With Efficient Mixture Of Diversified Trading Experts, Shuo Sun, Xinrun Wang, Wanqi Xue, Xiaoxuan Lou, Bo An

Research Collection School Of Computing and Information Systems

Quantitative stock investment is a fundamental financial task that highly relies on accurate prediction of market status and profitable investment decision making. Despite recent advances in deep learning (DL) have shown stellar performance on capturing trading opportunities in the stochastic stock market, the performance of existing DL methods is unstable with sensitivity to network initialization and hyperparameter selection. One major limitation of existing works is that investment decisions are made based on one individual neural network predictor with high uncertainty, which is inconsistent with the workflow in real-world trading firms. To tackle this limitation, we propose AlphaMix, a novel three-stage …

An Investigative Study On Quick Switching System Using Fuzzy And Neutrosophic Poisson Distribution, Uma G, Nandhitha S

Neutrosophic Systems with Applications

Stephens and Larson (1967) stated the sampling system as an allotted grouping of two or three sampling plans and the rules for switching between the plans for sentencing the lots of manufactured products. Quick Switching System (QSS) by Romboski (1969) is a sampling system with reference to the Single Sampling Plan (SSP) involves normal and tightened plans by adopting a switching rule. QSS provides quality protection and a reduction in the cost of inspection. The idea of fuzzy logic is adopted in the system to handle situations of fraction non-confirmation, uncertainty, or vagueness present in the parameters. The sampling plans …

Understanding Political Polarization Using Language Models: A Dataset And Method, Samiran Gode, Supreeth Bare, Bhiksha Raj, Hyungon Yoo

Natural Language Processing Faculty Publications

Our paper aims to analyze political polarization in US political system using language models, and thereby help candidates make an informed decision. The availability of this information will help voters understand their candidates' views on the economy, healthcare, education, and other social issues. Our main contributions are a dataset extracted from Wikipedia that spans the past 120 years and a language model-based method that helps analyze how polarized a candidate is. Our data are divided into two parts, background information and political information about a candidate, since our hypothesis is that the political views of a candidate should be based …

Survey Of Personalized Learning Software Systems: A Taxonomy Of Environments, Learning Content, And User Models, Heba Ismail, Nada Hussein, Saad Harous, Ashraf Khalil

All Works

This paper presents a comprehensive systematic review of personalized learning software systems. All the systems under review are designed to aid educational stakeholders by personalizing one or more facets of the learning process. This is achieved by exploring and analyzing the common architectural attributes among personalized learning software systems. A literature-driven taxonomy is recognized and built to categorize and analyze the reviewed literature. Relevant papers are filtered to produce a final set of full systems to be reviewed and analyzed. In this meta-review, a set of 72 selected personalized learning software systems have been reviewed and categorized based on the …

Neuro-Symbolic Representations For Information Retrieval, Laura Dietz, Hannah Bast, Shubham Chatterjee, Jeff Dalton, Jian Yun Nie, Rodrigo Nogueira

Computer Science Faculty Research & Creative Works

This tutorial will provide an overview of recent advances on neuro-symbolic approaches for information retrieval. A decade ago, knowledge graphs and semantic annotations technology led to active research on how to best leverage symbolic knowledge. At the same time, neural methods have demonstrated to be versatile and highly effective. From a neural network perspective, the same representation approach can service document ranking or knowledge graph reasoning. End-to-end training allows to optimize complex methods for downstream tasks. We are at the point where both the symbolic and the neural research advances are coalescing into neuro-symbolic approaches. The underlying research questions are …

Generative Relevance Feedback With Large Language Models, Iain Mackie, Shubham Chatterjee, Jeffrey Dalton

Computer Science Faculty Research & Creative Works

Current query expansion models use pseudo-relevance feedback to improve first-pass retrieval effectiveness; however, this fails when the initial results are not relevant. Instead of building a language model from retrieved results, we propose Generative Relevance Feedback (GRF) that builds probabilistic feedback models from long-form text generated from Large Language Models. We study the effective methods for generating text by varying the zero-shot generation subtasks: queries, entities, facts, news articles, documents, and essays. We evaluate GRF on document retrieval benchmarks covering a diverse set of queries and document collections, and the results show that GRF methods significantly outperform previous PRF methods. …

Detecting Mental Distresses Using Social Behavior Analysis In The Context Of Covid-19: A Survey, Sahraoui Dhelim, Liming Chen, Sajal K. Das, Huansheng Ning, Chris Nugent, Gerard Leavey, Dirk Pesch, Eleanor Bantry-White, Devin Michael Burns

Computer Science Faculty Research & Creative Works

Online social media provides a channel for monitoring people's social behaviors from which to infer and detect their mental distresses. During the COVID-19 pandemic, online social networks were increasingly used to express opinions, views, and moods due to the restrictions on physical activities and in-person meetings, leading to a significant amount of diverse user-generated social media content. This offers a unique opportunity to examine how COVID-19 changed global behaviors regarding its ramifications on mental well-being. In this article, we surveyed the literature on social media analysis for the detection of mental distress, with a special emphasis on the studies published …

An Interactional Account Of Empathy In Human-Machine Communication, Shauna Concannon, Ian Roberts, Marcus Tomalin

Human-Machine Communication

Efforts to develop empathetic agents, or systems capable of responding appropriately to emotional content, have increased as the deployment of such systems in socially complex scenarios becomes more commonplace. In the context of human-machine communication (HMC), the ability to create the perception of empathy is achieved in large part through linguistic behavior. However, studies of how language is used to display and respond to emotion in ways deemed empathetic are limited. This article aims to address this gap, demonstrating how an interactional linguistics informed methodological approach can be applied to the study of empathy in HMC. We present an analysis …

Enhancing Video-Based Learning Using Knowledge Tracing: Personalizing Students’ Learning Experience With Orbits, Shady Shehata, David Santandreu, Philip Purnell, Mark Thompson

Natural Language Processing Faculty Publications

As the world regains its footing following the COVID-19 pandemic, academia is striving to consolidate the gains made in students’ education experience. New technologies such as video-based learning have shown some early improvement in student learning and engagement. In this paper, we present ORBITS predictive engine at YOURIKA company, a video-based student support platform powered by knowledge tracing. In an exploratory case study of one master’s level Speech Processing course at the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) in Abu Dhabi, half the students used the system while the other half did not. Student qualitative feedback was universally …

Mitigating Landslide Hazards In Qena Governorate Of Egypt: A Gis-Based Neutrosophic Paprika Approach, Nabil M. Abdelaziz, Safa Al-Saeed

Neutrosophic Systems with Applications

This paper presents a novel approach to landslide susceptibility assessment in the Qena Governorate, Egypt, integrating the neutrosophic Multi-Criteria Decision-Making (MCDM) method, the Potentially All Pairwise RanKings of all possible Alternatives (PAPRIKA), and the ArcGIS weighted overlay technique. The research focuses on the quantification and prioritization of eight criteria: slope, aspect, proximity to road, soil type, proximity to river, land cover, elevation, and Lithology. These factors are evaluated under the uncertainty and indeterminacy of the neutrosophic environment by employing the PAPRIKA method. The results of the analysis are visualized and interpreted using ArcGIS weighted overlay, offering spatially explicit insights into …

“I Have Learned That Things Are Different Here”: Understanding The Transitional Challenges With Technology Use After Relocating To The Usa, Prakriti Dumaru, Ankit Shrestha, Rizu Paudel, Arezou Behfar, Hanieh Atashpanjeh, Mahdi Nasrullah Al-Ameen

Computer Science Student Research

In the age of globalization, international students from developing countries (for brevity, we term them as ‘international students’ in this paper, unless otherwise specified) have become an integral part of the U.S. education system. After relocation to the USA, first-generation international students undergo not only societal differences but also experience changes in the technology space – posing unique challenges for them. Our semi-structured interviews with 26 participants who were pursuing education at the time of our study, or had recently graduated informed us of their adaptation to the technology landscape in the USA; our analysis revealed the underlying challenges in …