Digital Commons Network^™

Peerda: Data Augmentation Via Modeling Peer Relation For Span Identification Tasks, Weiwen Xu, Xin Li, Yang Deng, Wai Lam, Lidong Bing

Research Collection School Of Computing and Information Systems

Span identification aims at identifying specific text spans from text input and classifying them into pre-defined categories. Different from previous works that merely leverage the Subordinate (SUB) relation (i.e. if a span is an instance of a certain category) to train models, this paper for the first time explores the Peer (PR) relation, which indicates that two spans are instances of the same category and share similar features. Specifically, a novel Peer Data Augmentation (PeerDA) approach is proposed which employs span pairs with the PR relation as the augmentation data for training. PeerDA has two unique advantages: (1) There are …

Product Question Answering In E-Commerce: A Survey, Yang Deng, Wenxuan Zhang, Qian Yu, Wai Lam

Research Collection School Of Computing and Information Systems

Product question answering (PQA), aiming to automatically provide instant responses to customer’s questions in E-Commerce platforms, has drawn increasing attention in recent years. Compared with typical QA problems, PQA exhibits unique challenges such as the subjectivity and reliability of user-generated contents in E-commerce platforms. Therefore, various problem settings and novel methods have been proposed to capture these special characteristics. In this paper, we aim to systematically review existing research efforts on PQA. Specifically, we categorize PQA studies into four problem settings in terms of the form of provided answers. We analyze the pros and cons, as well as present existing …

Goal Awareness For Conversational Ai: Proactivity, Non-Collaborativity, And Beyond, Yang Deng, Wenqiang Lei, Minlie Huang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Conversational systems are envisioned to provide social support or functional service to human users via natural language interactions. Conventional conversation researches mainly focus on the responseability of the system, such as dialogue context understanding and response generation, but overlooks the design of an essential property in intelligent conversations, i.e., goal awareness. The awareness of goals means the state of not only being responsive to the users but also aware of the target conversational goal and capable of leading the conversation towards the goal, which is a significant step towards higher-level intelligence and artificial consciousness. It can not only largely improve …

Augmenting Fake Content Detection In Online Platforms: A Domain Adaptive Transfer Learning Via Adversarial Training Approach, Ka Chung Ng, Ping Fan Ke, Mike K. P. So, Kar Yan Tam

Research Collection School Of Computing and Information Systems

Online platforms are experimenting with interventions such as content screening to moderate the effects of fake, biased, and incensing content. Yet, online platforms face an operational challenge in implementing machine learning algorithms for managing online content due to the labeling problem, where labeled data used for model training are limited and costly to obtain. To address this issue, we propose a domain adaptive transfer learning via adversarial training approach to augment fake content detection with collective human intelligence. We first start with a source domain dataset containing deceptive and trustworthy general news constructed from a large collection of labeled news …

Weakly Supervised Spatial Relation Extraction From Radiology Reports, Surabhi Datta, Kirk Roberts

Faculty, Staff and Student Publications

OBJECTIVE: Weak supervision holds significant promise to improve clinical natural language processing by leveraging domain resources and expertise instead of large manually annotated datasets alone. Here, our objective is to evaluate a weak supervision approach to extract spatial information from radiology reports.

MATERIALS AND METHODS: Our weak supervision approach is based on data programming that uses rules (or labeling functions) relying on domain-specific dictionaries and radiology language characteristics to generate weak labels. The labels correspond to different spatial relations that are critical to understanding radiology reports. These weak labels are then used to fine-tune a pretrained Bidirectional Encoder Representations from …

Neutrosophic Decision Making Model For Investment Portfolios Selection And Optimizing Based On Wide Variety Of Investment Opportunities And Many Criteria In Market, Ayman H. Abdel-Aziem, Hoda K. Mohamed, Ahmed Abdelhafeez

Neutrosophic Systems with Applications

Investment portfolio selection is a difficult subject due to the presence of competing factors. Choosing a portfolio for one's investments is a major choice that may have far-reaching effects on one's financial well-being. Risk tolerance, time horizon, investing objectives, asset allocation, and investment selection are only a few of the factors that will be studied in this article. The Stable Preference Ordering Towards Ideal Solution (SPOTIS) technique is the basis for our proposed integrated multi-criteria decision-making (MCDM) model. This paper used the single-valued neutrosophic set as a framework to deal with uncertain data. The purpose of the suggested SPOTIS–Neutrosophic model …

Deep Learning Model Compression Techniques: Advances, Opportunities, And Perspective, Hubert Msuya

Tanzania Journal of Engineering and Technology (TJET)

Recently, deep learning (DL) models have excelled in a wide range of fields. All of these successes are built on intricate DL models. The hundreds of millions or even billions of parameters and high-performance computing graphical processing units or tensor processing units are largely responsible for their achievement. DL model integration into real-time devices with tight latency limitations, limited memory, and power-constrained requirements is the key driving force behind investigation of DL model compression techniques. Also, there is an increase in data availability that encourages multimodal fusion in DL models to boost the models' predictive accuracy. In order to create …

Monitoring Personal Exposure To Air Quality Gradients While Biking On An Elevated Urban Trail, Gavin D. Salas

DePaul Discoveries

Air pollution is a major global health concern, specifically as it relates to the human exposome. The EPA criteria pollutants, including particulate matter (PM), carbon monoxide (CO), carbon dioxide (CO₂), and NO_x can have severe impacts on respiratory and cardiovascular health, particularly in populations with chronic illnesses such as asthma, those facing economic hardships and individuals who frequently spend time outdoors, such as bicyclists and runners. To understand the impact of air pollution on human health, it is essential to assess personal exposure. This study aimed to investigate personal exposure to air pollution levels while biking along …

2023 Chairs’ Welcome, Daniel Moreira, Aparna Bharati, Cecilia Pasquini, Yassine Yousfi

Computer Science: Faculty Publications and Other Works

Welcome to the 11th edition of the ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec ‘23). This year’s workshop continues the tradition of representing one of the prime events in information hiding and multimedia security, attracting researchers and practitioners worldwide. Carrying on with the efforts of the previous edition to overcome the Pandemics and reunite the IH&MMSec community to present and discuss their work, this year’s meeting is held fully in person at the Water Tower Campus of Loyola University Chicago, located right at the heart of the Windy City. Bathed by the fresh waters of Lake Michigan, Chicago …

Can You Answer This? - Exploring Zero-Shot Qa Generalization Capabilities In Large Language Models, Saptarshi Sengupta, Shreya Ghosh, Preslav Nakov, Prasenjit Mitra

Natural Language Processing Faculty Publications

The buzz around Transformer-based Language Models (TLMs) such as BERT, RoBERTa, etc. is well-founded owing to their impressive results on an array of tasks. However, when applied to areas needing specialized knowledge (closed-domain), such as medical, finance, etc. their performance takes drastic hits, sometimes more than their older recurrent/convolutional counterparts. In this paper, we explore zero-shot capabilities of large language models for extractive Question Answering. Our objective is to examine the performance change in the face of domain drift, i.e., when the target domain data is vastly different in semantic and statistical properties from the source domain, in an attempt …

Acquisition Of A Lexicon For Family History Information: Bidirectional Encoder Representations From Transformers-Assisted Sublanguage Analysis, Liwei Wang, Huan He, Andrew Wen, Sungrim Moon, Sunyang Fu, Kevin J Peterson, Xuguang Ai, Sijia Liu, Ramakanth Kavuluru, Hongfang Liu

Faculty, Staff and Student Publications

BACKGROUND: A patient's family history (FH) information significantly influences downstream clinical care. Despite this importance, there is no standardized method to capture FH information in electronic health records and a substantial portion of FH information is frequently embedded in clinical notes. This renders FH information difficult to use in downstream data analytics or clinical decision support applications. To address this issue, a natural language processing system capable of extracting and normalizing FH information can be used.

OBJECTIVE: In this study, we aimed to construct an FH lexical resource for information extraction and normalization.

METHODS: We exploited a transformer-based method to …

Graphprompt: Graph-Based Prompt Templates For Biomedical Synonym Prediction, Hanwen Xu, Jiayou Zhang, Zhirui Wang, Shizhuo Zhang, Megh Bhalerao, Yucong Liu, Dawei Zhu, Sheng Wang

Computer Vision Faculty Publications

In the expansion of biomedical dataset, the same category may be labeled with different terms, thus being tedious and onerous to curate these terms. Therefore, automatically mapping synonymous terms onto the ontologies is desirable, which we name as biomedical synonym prediction task. Unlike biomedical concept normalization (BCN), no clues from context can be used to enhance synonym prediction, making it essential to extract graph features from ontology. We introduce an expert-curated dataset OBO-syn encompassing 70 different types of concepts and 2 million curated concept-term pairs for evaluating synonym prediction methods. We find BCN methods perform weakly on this task for …

Stability-Based Generalization Analysis For Mixtures Of Pointwise And Pairwise Learning, Jiahuan Wang, Jun Chen, Hong Chen, Bin Gu, Weifu Li, Xin Tang

Machine Learning Faculty Publications

Recently, some mixture algorithms of pointwise and pairwise learning (PPL) have been formulated by employing the hybrid error metric of “pointwise loss + pairwise loss” and have shown empirical effectiveness on feature selection, ranking and recommendation tasks. However, to the best of our knowledge, the learning theory foundation of PPL has not been touched in the existing works. In this paper, we try to fill this theoretical gap by investigating the generalization properties of PPL. After extending the definitions of algorithmic stability to the PPL setting, we establish the high-probability generalization bounds for uniformly stable PPL algorithms. Moreover, explicit convergence …

Probing As A Technique To Understand Abstract Spaces, Ashlen A. Plasek

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

Machine learning models, while very powerful, have their operation obfuscated behind millions of parameters. This obfuscation can make deriving a human meaningful process from a machine learning model very difficult. However, while the intermediate states of a machine learning model are similarly obfuscated, using probing, we can start to explore looking at possible structure in those intermediate states. Large language models are a prime example of this obfuscation, and probing can begin to allow novel experimentation to be performed.

Identify The Most Productive Crop To Encourage Sustainable Farming Methods In Smart Farming Using Neutrosophic Environment, Ahmed Abdelhafeez, Hadeer Mahmoud, Alber S. Aziz

Neutrosophic Systems with Applications

Only with careful management can the data provided by crops be used to make smart, profitable choices. Data has become the central ingredient in contemporary agriculture, and the recent advancements in handling it are contributing greatly to the meteoric rise of smart farming. Gains in efficiency and longevity may be realized to a significant degree by using the objective data collected by sensors. These data-driven farms can maximize output while minimizing waste and environmental impact thanks to the information they collect and analyze. Various criteria and factors in smart farming can aid in productivity. Sensors, drones, Global Positioning System (GPS) …

The Use Of Artificial Intelligence In Higher Education: A Study On Faculty Perspectives In Universities In Egypt, Farah S. Sharawy

Theses and Dissertations

Artificial Intelligence (AI) is an emerging technology that is transforming various aspects of society, including higher education. This paper examines faculty perspectives from five different institutions; The American University in Cairo (AUC), The German University in Cairo (GUC), The Arab Academy for Science and Technology (AAST), Ain Shams University, and Cairo University, on the use of AI in higher education in teaching and learning in Egypt, with all its challenges and resources available to support it, and how it can be used to achieve equity and accessibility. This research was conducted through a qualitative study using semi-structured one- on-one interviews …

Using Ai-Generated Suggestions From Chatgpt To Optimize Clinical Decision Support, Siru Liu, Aileen P Wright, Barron L Patterson, Jonathan P Wanderer, Robert W Turer, Scott D Nelson, Allison B Mccoy, Dean F Sittig, Adam Wright

Faculty, Staff and Student Publications

OBJECTIVE: To determine if ChatGPT can generate useful suggestions for improving clinical decision support (CDS) logic and to assess noninferiority compared to human-generated suggestions.

METHODS: We supplied summaries of CDS logic to ChatGPT, an artificial intelligence (AI) tool for question answering that uses a large language model, and asked it to generate suggestions. We asked human clinician reviewers to review the AI-generated suggestions as well as human-generated suggestions for improving the same CDS alerts, and rate the suggestions for their usefulness, acceptance, relevance, understanding, workflow, bias, inversion, and redundancy.

RESULTS: Five clinicians analyzed 36 AI-generated suggestions and 29 human-generated suggestions …

Grm: Generative Relevance Modeling Using Relevance-Aware Sample Estimation For Document Retrieval, Iain Mackie, Ivan Sekulic, Shubham Chatterjee, Jeffrey Dalton, Fabio Crestani

Computer Science Faculty Research & Creative Works

Recent studies show that Generative Relevance Feedback (GRF), using text generated by Large Language Models (LLMs), can enhance the effectiveness of query expansion. However, LLMs can generate irrelevant information that harms retrieval effectiveness. To address this, we propose Generative Relevance Modeling (GRM) that uses Relevance-Aware Sample Estimation (RASE) for more accurate weighting of expansion terms. Specifically, we identify similar real documents for each generated document and use a neural re-ranker to estimate their relevance. Experiments on three standard document ranking benchmarks show that GRM improves MAP by 6-9% and R@1k by 2-4%, surpassing previous methods.

Aisha: A Custom Ai Library Chatbot Using The Chatgpt Api, Yrjo Lappalainen, Nikesh Narayanan

All Works

This article focuses on the development of a custom chatbot for Zayed University Library (United Arab Emirates) using Python and the ChatGPT API. The chatbot, named Aisha, was designed to provide quick and efficient reference and support services to students and faculty outside the library's regular operating hours. The article also discusses the benefits of chatbots in academic libraries, and reviews the early literature on ChatGPT's applicability in this field. The article describes the development process, perceived capabilities and limitations of the bot, and plans for further development. This project represents the first fully reported attempt to explore the potential …

Math Attitudes And Identity Of High Schoolers Impacted Through Participating In Informal, Near-Peer Mentoring, Aaron T. Wilson, Xiaohui Wang, Mayra Ortiz Galarza, John Knight, Eliazar Patiño

School of Mathematical & Statistical Sciences Faculty Publications

Research in mentoring has shown that students may at times be more willing and able to absorb information that is delivered to them by their near-peers, rather than by traditional figures of authority, like teachers and professors. In this study, underrepresented minority high school students participated in an informal learning experience that was led by college students who were "near-peers" to the high schoolers. Students were engaged by participating in interactive MathShows, following a Math Social Media Campaign, and attending a summer Math Internship. Participants in the quantitative component of the study included N = 559 U.S. high schoolers who …

Towards An Experimental Bibliography Of Hemispheric Reconstruction Newspapers, Joshua Ortiz Baco, Benjamin Charles Germain Lee, Jim Casey, Sarah H. Salter

Criticism

Digital collections of newspapers have drawn broader attention to the fragmented and scattered print histories of minoritized communities. Attempts to survey these histories through bibliography, however, quickly meet with a fundamental problem: the practice of bibliographic description calls for creating a static record of social affiliations. Given the overwhelming scholarly consensus that categories such as race, ethnicity, and language are socially constructed, this article introduces an experimental bibliographic method for mapping the vast landscape of historical newspapers. This method extends the machine learning affordances of a recent project called Newspaper Navigator to enumerate the newspapers in Chronicling America according to …

Comparison Of The Unweighted Log-Rank And Weighted Prentice-Modified Wilcoxon Tests With Left-Truncated Data, Ellen Wight

Undergraduate Honors Theses

In survival analysis, there is a potential interaction between left-truncated data and rank test procedures for the difference between two groups that has not yet been investigated in depth. This study explores the effect of left truncation on the absolute and relative performance of the unweighted log-rank test and the weighted Prentice modification of the Gehan-Wilcoxon test. Resulting power from simulation study replications revealed that while left truncation does not affect which test performs better overall, it does affect the relative difference between the tests. It significantly worsens the individual performance of the Prentice-modified test, likely because of left truncation …

Contextualizing The Mathematical Knowledge For Teaching Framework For Teachers Of Emergent Bilinguals, Luis M. Fernandez, Mayra Ortiz Galarza

School of Mathematical & Statistical Sciences Faculty Publications

We are amid a rapid demographic shift, with Emergent Bilinguals (EBs) being the fastest growing K-12 student population. This has created an ambitious goal for teacher education programs as they must prepare mathematics pre-service teachers (PSTs) to assess the needs of EBs. As a response, this study conducted a qualitative analysis of 16 PSTs to propose a contextualized version of the Mathematical Knowledge for Teaching (MKT) framework as an emerging knowledge base of teaching that can be used to further guide the planning and enactment of teacher education programs in the mathematics education of EBs, specifically.

Quantifying Implicit Bias In Judicial Legal Opinions: A Natural Language Processing Approach, Philip N. Surendran

Quantitative Social Science Undergraduate Senior Theses

Implicit bias and criminal justice are two concepts that have long been intertwined. There is no justice without neutrality, and yet how do we tell if the actors enforcing the system are actually impartial? In this thesis, I utilize recent advancements in machine learning to attempt to answer this question. Specifically, I use natural language processing to examine the text of opinions written by judges in appellate courts, and I leverage these findings to build quantifiable measures of implicit bias. In particular, I look at the over/under-representation of certain emotions, sentiments and linguistic styles as a proxy for disparate treatment …

Stereotypes And Language Models: Understanding How Language Models Encode Stereotypes, Debiasing Language Models, And Examining How Stereotypes Affect Conversations, Brian C. Wang

Computer Science Senior Theses

This thesis describes a variety of approaches in examining how language models encode stereotypes (understanding stereotypes from a model point-of-view), debiasing language models, and using language models to understand how stereotypes affect conversations (understanding stereotypes from a conversational point-of-view). We present a novel approach for textual clues analysis that makes language models more interpretable, combining the understanding of what stereotypes the internal structures of language models have encoded during their initial training (via attention-based analysis) and understanding what textual clues are most relevant to identifying stereotypes for models trained to detect stereotypes (via SHAP-based analysis). We find that different pre-trained …

Sarcasm Detection In English And Arabic Tweets Using Transformer Models, Rishik Lad

Computer Science Senior Theses

This thesis describes our approach toward the detection of sarcasm and its various types in English and Arabic Tweets through methods in deep learning. There are five problems we attempted: (1) detection of sarcasm in English Tweets, (2) detection of sarcasm in Arabic Tweets, (3) determining the type of sarcastic speech subcategory for English Tweets, (4) determining which of two semantically equivalent English Tweets is sarcastic, and (5) determining which of two semantically equivalent Arabic Tweets is sarcastic. All tasks were framed as classification problems, and our contributions are threefold: (a) we developed an English binary classifier system with RoBERTa, …

Counterfactual Replacement Analysis For Interpretation Of Blackbox Sexism Classification Models, Anders Knospe

Computer Science Senior Theses

This paper describes the AKD team’s system designed for SemEval-2023 Task 10: Explainable Detection of Online Sexism (EDOS). We implement a simple fine-tuned GPT-3 model, ranking 26 on the leaderboard for task A. We also discuss different approaches to interpretability in the context of critiquing the EDOS task’s sub-category oriented approach. Finally, we propose counterfactual replacement analysis, a novel prototype technique for approaching explainability.

Dialogs Re-Enacted Across Languages, Version 2, Nigel G. Ward, Jonathan E. Avila, Emilia Rivas, Divette Marco

Departmental Technical Reports (CS)

To support machine learning of cross-language prosodic mappings and other ways to improve speech-to-speech translation, we present a protocol for collecting closely matched pairs of utterances across languages, a description of the resulting data collection and its public release, and some observations and musings. This report is intended for:

• people using this corpus
• people extending this corpus
• people designing similar collections of bilingual dialog data.

Change Notes. This version supersedes UTEP-CS-22-108. There is some new information and numerous clarifications, mostly arising from our experiences diversifying our corpus and helping a vendor to use this protocol.

Exploiting Association Rules Mining To Inform The Use Of Non-Manual Features In Sign Language Processing, Robert G. Smith

Other Resources

In recent years, the use of virtual assistants and voice user interfaces has become a latent part of modern living. Unseen to the user are the various artificial intelligence and natural language processing technologies, the vast datasets, and the linguistic insights that underpin such tools. The technologies supporting them have chiefly targeted widely used spoken languages, leaving sign language users at a disadvantage. One important reason why sign languages are unsupported by such tools is a requirement of the underpinning technologies for a comprehensive description of the language. Sign language processing technologies endeavour to bridge this technology inequality.

Recent approaches …

Neural Tabula Rasa: Foundations For Realistic Memories And Learning, Patrick R. Perrine

Master's Theses

Understanding how neural systems perform memorization and inductive learning tasks are of key interest in the field of computational neuroscience. Similarly, inductive learning tasks are the focus within the field of machine learning, which has seen rapid growth and innovation utilizing feedforward neural networks. However, there have also been concerns regarding the precipitous nature of such efforts, specifically in the area of deep learning. As a result, we revisit the foundation of the artificial neural network to better incorporate current knowledge of the brain from computational neuroscience. More specifically, a random graph was chosen to model a neural system. This …