Digital Commons Network^™

Shapley Idioms: Analysing Bert Sentence Embeddings For General Idiom Token Identification, Vasudevan Nedumpozhimana, Filip Klubicka, John Kelleher

Articles

This article examines the basis of Natural Language Understanding of transformer based language models, such as BERT. It does this through a case study on idiom token classification. We use idiom token identification as a basis for our analysis because of the variety of information types that have previously been explored in the literature for this task, including: topic, lexical, and syntactic features. This variety of relevant information types means that the task of idiom token identification enables us to explore the forms of linguistic information that a BERT language model captures and encodes in its representations. The core of …

Estimating Fuel-Efficient Air Plane Trajectories Using Machine Learning, Jaiteg Singh, Gaurav Goyal, Farman Ali, Babar Shah, Sangheon Pack

All Works

Airline industry has witnessed a tremendous growth in the recent past. Percentage of people choosing air travel as first choice to commute is continuously increasing. Highly demanding and congested air routes are resulting in inadvertent delays, additional fuel consumption and high emission of greenhouse gases. Trajectory planning involves creation identification of cost-effective flight plans for optimal utilization of fuel and time. This situation warrants the need of an intelligent system for dynamic planning of optimized flight trajectories with least human intervention required. In this paper, an algorithm for dynamic planning of optimized flight trajectories has been proposed. The proposed algorithm …

Investigating How Speech And Animation Realism Influence The Perceived Personality Of Virtual Characters And Agents, Sean A. Thomas, Ylva Ferstl, Rachel Mcdonnell, Cathy Ennis

Articles

The portrayed personality of virtual characters and agents is understood to influence how we perceive and engage with digital applications. Understanding how the features of speech and animation drive portrayed personality allows us to intentionally design characters to be more personalized and engaging. In this study, we use performance capture data of unscripted conversations from a variety of actors to explore the perceptual outcomes associated with the modalities of speech and motion. Specifically, we contrast full performance-driven characters to those portrayed by generated gestures and synthesized speech, analysing how the features of each influence portrayed personality according to the Big …

Utilization Of Virtual Reality For General Education Purposes, Amit Lal

University of the Pacific Theses and Dissertations

The use of Virtual Reality (VR) in a variety of professional, military, governmental, and educational fields has continued to expand over the past several decades, and the recent Covid-19 pandemic has brought attention to this field. This study surveys 154 college students over 23 questions that include various demographics that can be used to look for discriminators, multiple-choice VR-related questions, as well as a few free-form questions about use of VR in learning environments. The students’ experience with, interest in, and thoughts on how to best use VR vary considerably. The Covid-19 pandemic is found to have limited impact thus …

Novel Primitive Decompositions For Real-World Physical Reasoning, Mackie Zhoou, Bridget Duah, Jamie C. Macbeth

Computer Science: Faculty Publications

In this work, we are concerned with developing cognitive representations that may en- hance the ability for self-supervised learning systems to learn language as part of their world explorations. We apply insights from in-depth language understanding systems to the problem, specifically representations which decompose language inputs into language-free structures that are complex combinations of primitives representing cognitive abstractions such as object permanence, movement, and spatial relationships. These decompositions, performed by a system traditionally called a conceptual analyzer, link words with complex non-linguistic structures that engender the rich relations between language expressions and world exploration that are a familiar aspect of …

Interleaving A Symbolic Story Generator With A Neural Network-Based Large Language Model, Jingwen Xiang, Zoie Zhao, Mackie Zhou, Megan Mckenzie, Alexis Kilayko, Jamie C. Macbeth, Scott Carter, Katharine Sieck, Matthew Klenk

Computer Science: Faculty Publications

Research in deep learning has recently produced models of natural language that are capable of generating natural language output which, at a glance, has strong similarities to that written by intelligent humans. However, the texts produced by deep learning-based large language models (LLMs), upon deeper examination, reveal the challenges that they have in producing outputs that maintain logical coherence. One specific application area of interest for LLMs is in fictional narrative generation, a mode of operation in which stories are generated by the model in response to a prompt text that indicates the start of a story or the desired …

Interest Points Analysis For Internet Forum Based On Long-Short Windows Similarity, Xinghai Ju, Jicang Lu, Xiangyang Luo, Gang Zhou, Shiyu Wang, Shunhang Li, Yang Yang

Research Collection School Of Computing and Information Systems

For Internet forum Points of Interest (PoI), existing analysis methods are usually lack of usability analysis under different conditions and ignore the long-term variation, which lead to blindness in method selection. To address this problem, this paper proposed a PoI variation prediction framework based on similarity analysis between long and short windows. Based on the framework, this paper presented 5 PoI analysis algorithms which can be categorized into 2 types, i.e., the traditional sequence analysis methods such as autoregressive integrated moving average model (ARIMA), support vector regressor (SVR), and the deep learning methods such as convolutional neural network (CNN), long-short …

Exposing And Fixing Causes Of Inconsistency And Nondeterminism In Clustering Implementations, Xin Yin

Dissertations

Cluster analysis aka Clustering is used in myriad applications, including high-stakes domains, by millions of users. Clustering users should be able to assume that clustering implementations are correct, reliable, and for a given algorithm, interchangeable. Based on observations in a wide-range of real-world clustering implementations, this dissertation challenges the aforementioned assumptions.

This dissertation introduces an approach named SmokeOut that uses differential clustering to show that clustering implementations suffer from nondeterminism and inconsistency: on a given input dataset and using a given clustering algorithm, clustering outcomes and accuracy vary widely between (1) successive runs of the same toolkit, i.e., nondeterminism, and …

A Framework Of Web-Based Dark Patterns That Can Be Detected Manually Or Automatically, Ioannis Stavrakakis, Andrea Curley, Dympna O'Sullivan, Damian Gordon, Brendan Tierney

Articles

This research explores the design and development of a framework for the detection of Dark Patterns, which are a series of user interface tricks that manipulate users into actions that they do not intend to do, for example, share more data than they want to, or spend more money than they plan to. The interface does this using either deception or other psychological nudges. User Interface experts have categorized a number of these tricks that are commonly used and have called them Dark Patterns. They are typically varied in their form and what they do, and the goal of this …

On The Documentation Of Refactoring Types, Eman Abdullah Alomar, Jiaqian Liu, Kenneth Addo, Mohamed Wiem Mkaouer, Christian D. Newman, Ali Ouni, Zhe Yu

Articles

Commit messages are the atomic level of software documentation. They provide a natural language description of the code change and its purpose. Messages are critical for software maintenance and program comprehension. Unlike documenting feature updates and bug fixes, little is known about how developers document their refactoring activities. Specifically, developers can perform multiple refactoring operations, including moving methods, extracting classes, renaming attributes, for various reasons, such as improving software quality, managing technical debt, and removing defects. Yet, there is no systematic study that analyzes the extent to which the documentation of refactoring accurately describes the refactoring operations performed at the …

An Open Source Direct Messaging And Enhanced Recommendation System For Yioop, Aniruddha Dinesh Mallya

Master's Projects

Recommendation systems and direct messaging systems are two popular components of web portals. A recommendation system is an information filtering system that seeks to predict the "rating" or "preference" a user would give to an item and a direct messaging system allows private communication between users of any platform. Yioop, is an open source, PHP search engine and web portal that can be configured to allow users to create discussion groups, blogs, wikis etc.

In this project, we expanded on Yioop’s group system so that every user now has a personal group. Personal groups were then used to add user …

Employee Churn Prediction Using Logistic Regression And Support Vector Machine, Rajendra Maharjan

Master's Projects

It is a challenge for Human Resource (HR) team to retain their existing employees than to hire a new one. For any company, losing their valuable employees is a loss in terms of time, money, productivity, and trust, etc. This loss could be possibly minimized if HR could beforehand find out their potential employees who are planning to quit their job hence, we investigated solving the employee churn problem through the machine learning perspective. We have designed machine learning models using supervised and classification-based algorithms like Logistic Regression and Support Vector Machine (SVM). The models are trained with the IBM …

Proquest Tdm Studio: A Text And Data Mining Solution, Anamika Megwalu, Anne Marie Engelsen

Faculty Research, Scholarly, and Creative Activity

TDM Studio is an integrated platform offered by ProQuest for data and text mining. TDM stands for text and data mining. This cloud-based, all-in-one innovative product is designed to offer researchers a clean interface with rights-cleared content, Jupyter notebook, and data visualization tools. As a result, researchers can now search Pro-Quest databases, create large datasets, import data to Jupyter notebook for analysis, and download results within a day.

The Detection Of Sexual Harassment And Chat Predators Using Artificial Neural Network, Noor Amer Hamzah, Ban N. Dhannoon

Karbala International Journal of Modern Science

The vast increase in using social media sites like Twitter and Facebook led to frequent sexual_harassment on the Internet, which is considered a major societal problem. This paper aims to detect sexual_harassment and cyber_predators in early phase. We used deeplearning like Bidirectionally-long-short-term memory. Word representations are carefully reviewed in text specific to mapping to real number vectors. The chat sexual predators Detection_approach with the proposed_model. The best results obtained by the performance measured with F0.5-score were the result is_0.927 with proposed_models. The accuracy measured is_97.27% in the proposed_model. The comments sexual_harassment Detection_approach the result is_0.925 F0.5-score, and accuracy measured is_99.12%.

Gr-118 - Sentiment Analysis On Hotel Review, Navya Pallapothu, Aravinda Pandanaboyana, Dilip Kumar

C-Day Computing Showcase

No abstract provided.

Semantically Meaningful Sentence Embeddings, Rojina Deuja

School of Computing: Dissertations, Theses, and Student Research

Text embedding is an approach used in Natural Language Processing (NLP) to represent words, phrases, sentences, and documents. It is the process of obtaining numeric representations of text to feed into machine learning models as vectors (arrays of numbers). One of the biggest challenges in text embedding is representing longer text segments like sentences. These representations should capture the meaning of the segment and the semantic relationship between its constituents. Such representations are known as semantically meaningful embeddings. In this thesis, we seek to improve upon the quality of sentence embeddings that capture semantic information.

The current state-of-the-art models are …

Negations Of Probability Distributions: A Survey, Ildar Z. Baryrshin, Nailya I. Kubysheva, Venera R. Bayrasheva, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

In recent years many papers have been devoted to the analysis and applications of negations of finite probability distributions (PD), first considered by Ronald Yager. This paper gives a brief overview of some formal results on the definition and properties of negations of PD. Negations of PD are generated by negators of probability values transforming element-by-element PD into a negation of PD. Negators are non-increasing functions of probability values. There are two types of negators: PD-independent and PD-dependent negators. Yager's negator is fundamental in the characterization of linear PD-independent negators as a convex combination of Yager's negator and uniform negator. …

Human Behavior In Domestic Environments: Prediction And Applications, Sharare Zehtabian

Electronic Theses and Dissertations, 2020-2023

A longstanding goal of human behavior science is to model and predict how humans interact with each other or with other systems. Such models are beneficial and have many applications, including designing and implementing assistive technologies, improving users' experiences and quality of life and making better decisions to create public policies. Behavior is highly complex due to uncertainties and a lack of scientific tools to measure it. Hence prediction of human behavior cannot be 100% accurate. However, prediction is also not hopeless because the biological needs, as well as cultural conventions (for instance, regarding meal times) set the general patterns …

Machine Learning Techniques For Topic Detection And Authorship Attribution In Textual Data, Fereshteh Jafariakinabad

Electronic Theses and Dissertations, 2020-2023

The unprecedented expansion of user-generated content in recent years demands more attempts of information filtering in order to extract high-quality information from the huge amount of available data. In this dissertation, we begin with a focus on topic detection from microblog streams, which is the first step toward monitoring and summarizing social data. Then we shift our focus to the authorship attribution task, which is a sub-area of computational stylometry. It is worth mentioning that determining the style of a document is orthogonal to determining its topic, since the document features which capture the style are mainly independent of its …

Early Prediction Of Hate Speech Propagation, Ken-Yu Lin, Roy Ka-Wei Lee, Wei Gao, Wen-Chih Peng

Research Collection School Of Computing and Information Systems

Online hate speech has disrupted the social connectedness in online communities and raises public safety concerns in our societies. Motivated by this rising issue, researchers have developed many machine learning and deep learning methods to detect hate speech in social media automatically. However, most of the existing automated solutions have focused on detecting hate speech in a single post, neglecting the network and information propagation effects of social media platforms. Ideally, the content moderators would want to identify the hateful posts and monitor posts and threads that are likely to induce hate. This paper aims to address this research gap …

Self-Supervised Learning Disentangled Group Representation As Feature, Tan Wang, Zhongqi Yue, Jianqiang Huang, Qianru Sun, Hanwang Zhang

Research Collection School Of Computing and Information Systems

A good visual representation is an inference map from observations (images) to features (vectors) that faithfully reflects the hidden modularized generative factors (semantics). In this paper, we formulate the notion of “good” representation from a group-theoretic view using Higgins’ definition of disentangled representation [38], and show that existing Self-Supervised Learning (SSL) only disentangles simple augmentation features such as rotation and colorization, thus unable to modularize the remaining semantics. To break the limitation, we propose an iterative SSL algorithm: Iterative Partition-based Invariant Risk Minimization (IP-IRM), which successfully grounds the abstract semantics and the group acting on them into concrete contrastive learning. …

Etherlearn: Decentralizing Learning Via Blockchain, Nguyen Binh Duong Ta, Tian Jun Joel Yang

Research Collection School Of Computing and Information Systems

In institutes of higher learning, most of the time course material development and delivery follow a centralized model which is fully lecturer-controlled. In this model, engaging students as partners in learning is a challenging problem as: 1) students are usually hesitant to contribute due to the fear of getting it wrong, 2) not much incentive for them to put in the extra effort, and 3) current online learning systems lack adequate facilities to support seamless and anonymous interactions between students. In this work, we propose EtherLearn, a blockchain based peer-learning system to distribute the control of how course material and …

Graph Learning Assisted Multi-Objective Integer Programming, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang, Abhishek Gupta, Mingyan Simon Lin

Research Collection School Of Computing and Information Systems

Objective-space decomposition algorithms (ODAs) are widely studied for solvingmulti-objective integer programs. However, they often encounter difficulties inhandling scalarized problems, which could cause infeasibility or repetitive nondominatedpoints and thus induce redundant runtime. To mitigate the issue, we presenta graph neural network (GNN) based method to learn the reduction rule in the ODA.We formulate the algorithmic procedure of generic ODAs as a Markov decisionprocess, and parameterize the policy (reduction rule) with a novel two-stage GNNto fuse information from variables, constraints and especially objectives for betterstate representation. We train our model with imitation learning and deploy it ona state-of-the-art ODA. Results show that …

From Language Comprehension Towards General Ai, Binay Dahal

UNLV Theses, Dissertations, Professional Papers, and Capstones

Language comprehension or more formally, natural language understanding is one of the major undertakings in Artificial Intelligence. In this work, we explore a few of the problems in language understanding using fixed deep learning models. Specifically, first, we look into question generation. Asking questions relates to the cognitive ability of language comprehension and context understanding. For that reason, making progress in question generation is significant. We introduce a novel task called “question generation with masked target answer” and propose various models and present the baseline result for the task. Next, we extend on the question generation task and develop a …

Theoretical Models Of Integration Of Interactive Learning Technologies Into Teaching: A Systematic Literature Review, Laila Mohebi

All Works

With the fast progress of technology and the vast amount of research papers related to technology integration in education being published yearly, a study that reviews models used in these papers is needed. Therefore, this paper (1) reviewed and analysed theoretical frameworks with models used for integration of technology in classrooms, (2) reviewed studies that discussed the impact of technology integration on students' learning capabilities, and (3) discussed the importance of preparing teachers to effectively integrate technology in teaching. The models reviewed were: Teacher Thoughts and Action Process (TTAP), Theory of Planned Behavior, Expectancy-Value Theory of Achievement Motivation (EVAM), Substitution …

Enhancing The Performance Of Text Mining, Farah Mahmoud Al Shanik

All Dissertations

The amount of text data produced in science, finance, social media, and medicine is growing at an unprecedented pace. The raw text data typically introduces major computational and analytical obstacles (e.g., extremely high dimensionality) to data mining and machine learning algorithms. Besides, the growth in the size of text data makes the search process more difficult for information retrieval systems, making retrieving relevant results to match the users’ search queries challenging. Moreover, the availability of text data in different languages creates the need to develop new methods to analyze multilingual topics to help policymakers in governmental and health systems to …

Notions Of Explainability And Evaluation Approaches For Explainable Artificial Intelligence, Giulia Vilone, Luca Longo

Articles

Explainable Artificial Intelligence (XAI) has experienced a significant growth over the last few years. This is due to the widespread application of machine learning, particularly deep learning, that has led to the development of highly accurate models that lack explainability and interpretability. A plethora of methods to tackle this problem have been proposed, developed and tested, coupled with several studies attempting to define the concept of explainability and its evaluation. This systematic review contributes to the body of knowledge by clustering all the scientific studies via a hierarchical system that classifies theories and notions related to the concept of explainability …

Russian Logics And The Culture Of Impossible: Part 1. Recovering Intelligentsia Logics, Ksenia Tatarchenko, Anya Yermakova, Liesbeth De Mol

Research Collection College of Integrative Studies

This article reinterprets algorithmic rationality by looking at the interaction between mathematical logic, mechanized reasoning, and, later, computing in the Russian Imperial and Soviet contexts to offer a history of the algorithm as a mathematical object bridging the inner and outer worlds, a humanistic vision that we, following logician Vladimir Uspensky, call the “culture of the impossible.” We unfold the deep roots of this vision as embodied in scientific intelligentsia. In Part I, we examine continuities between the turn-of-the-twentieth-century discussions of poznaniye—an epistemic orientation towards the process of knowledge acquisition—and the postwar rise of the Soviet school of mathematical logic. …

Learning To Iteratively Solve Routing Problems With Dual-Aspect Collaborative Transformer, Yining Ma, Jingwen Li, Zhiguang Cao, Wen Song, Le Zhang, Zhenghua Chen, Jing Tang

Research Collection School Of Computing and Information Systems

Recently, Transformer has become a prevailing deep architecture for solving vehicle routing problems (VRPs). However, it is less effective in learning improvement models for VRP because its positional encoding (PE) method is not suitable in representing VRP solutions. This paper presents a novel Dual-Aspect Collaborative Transformer (DACT) to learn embeddings for the node and positional features separately, instead of fusing them together as done in existing ones, so as to avoid potential noises and incompatible correlations. Moreover, the positional features are embedded through a novel cyclic positional encoding (CPE) method to allow Transformer to effectively capture the circularity and symmetry …

Towards Understanding Why Lookahead Generalizes Better Than Sgd And Beyond, Pan Zhou, Hanshu Yan, Xiaotong Yuan, Jiashi Feng, Shuicheng Yan

Research Collection School Of Computing and Information Systems

To train networks, lookahead algorithm [1] updates its fast weights k times via an inner-loop optimizer before updating its slow weights once by using the latest fast weights. Any optimizer, e.g. SGD, can serve as the inner-loop optimizer, and the derived lookahead generally enjoys remarkable test performance improvement over the vanilla optimizer. But theoretical understandings on the test performance improvement of lookahead remain absent yet. To solve this issue, we theoretically justify the advantages of lookahead in terms of the excess risk error which measures the test performance. Specifically, we prove that lookahead using SGD as its inner-loop optimizer can …