Digital Commons Network^™

Building And Using Digital Libraries For Etds, Edward A. Fox

The Journal of Electronic Theses and Dissertations

Despite the high value of electronic theses and dissertations (ETDs), the global collection has seen limited use. To extend such use, a new approach to building digital libraries (DLs) is needed. Fortunately, recent decades have seen that a vast amount of “gray literature” has become available through a diverse set of institutional repositories as well as regional and national libraries and archives. Most of the works in those collections include ETDs and are often freely available in keeping with the open-access movement, but such access is limited by the services of supporting information systems. As explained through a set of …

“When They Say Weed Causes Depression, But It’S Your Fav Antidepressant”: Knowledge-Aware Attention Framework For Relationship Extraction, Shweta Yadav, Usha Lokala, Raminta Daniulaityte, Krishnaprasad Thirunarayan, Francois Lamy, Amit P. Sheth

Faculty Publications

With the increasing legalization of medical and recreational use of cannabis, more research is needed to understand the association between depression and consumer behavior related to cannabis consumption. Big social media data has potential to provide deeper insights about these associations to public health analysts. In this interdisciplinary study, we demonstrate the value of incorporating domain-specific knowledge in the learning process to identify the relationships between cannabis use and depression. We develop an end-to-end knowledge infused deep learning framework (Gated-K-BERT) that leverages the pre-trained BERT language representation model and domain-specific declarative knowledge source (Drug Abuse Ontology) to jointly extract entities …

Neuro-Symbolic Deductive Reasoning For Cross-Knowledge Graph Entailment, Monireh Ebrahimi, Md Kamruzzaman Sarker, Federico Bianchi, Ning Xie, Aaron Eberhart, Derek Doran, Hyeongsik Kim, Pascal Hitzler

Computer Science and Engineering Faculty Publications

A significant and recent development in neural-symbolic learning are deep neural networks that can reason over symbolic knowledge graphs (KGs). A particular task of interest is KG entailment, which is to infer the set of all facts that are a logical consequence of current and potential facts of a KG. Initial neural-symbolic systems that can deduce the entailment of a KG have been presented, but they are limited: current systems learn fact relations and entailment patterns specific to a particular KG and hence do not truly generalize, and must be retrained for each KG they are tasked with entailing. We …

Topic-Centric Unsupervised Multi-Document Summarization Of Scientific And News Articles, Amanuel Alambo, Cori Lohstroh, Erik Madaus, Swati Padhee, Brandy Foster, Tanvi Banerjee, Krishnaprasad Thirunarayan, Michael Raymer

Computer Science and Engineering Faculty Publications

Recent advances in natural language processing have enabled automation of a wide range of tasks, including machine translation, named entity recognition, and sentiment analysis. Automated summarization of documents, or groups of documents, however, has remained elusive, with many efforts limited to extraction of keywords, key phrases, or key sentences. Accurate abstractive summarization has yet to be achieved due to the inherent difficulty of the problem, and limited availability of training data. In this paper, we propose a topic-centric unsupervised multi-document summarization framework to generate extractive and abstractive summaries for groups of scientific articles across 20 Fields of Study (FoS) in …

Polymorphism And Polysemy In Images Of The Sefirot, Martin Zwick

Complex Systems Faculty Publications and Presentations

The resurgence of interest in Kabbalistic diagrams (Segol, Busi, Chajes) raises the question of how diagrams function in religious symbolism. This question can be approached via methods used in the graphical modeling of data. Specifically, graph theory lets one define a repertoire of candidate structures that can be applied not only to quantitative data, but also to symbols consisting of qualitative components. A graph is a set of nodes and links between nodes. What nodes and links are is unspecified in this definition. The Kabbalistic Ilan is – partially – a graph. The Sefirot are its nodes; the paths connecting …

Exploring The Use Of Neural Transformers For Psycholinguistics, Antonio Laverghetta Jr.

USF Tampa Graduate Theses and Dissertations

Deep learning has the potential to help solve numerous problems in cognitive science andeducation, by providing us a way to model the cognitive profiles of individual people. If this were possible, it would allow us to design targeted tests and suggest specific remediation based on each individual’s needs. On the flip side, employing techniques from psychology can give us insight into the underlying skillsets neural networks have acquired during training, addressing the interpretability concern. This thesis explores these ideas in the context of transformer language models, which have achieved state-of-the-art results on virtually every natural language processing (NLP) task. First, …

How To Best Write Research Papers: Basic English? Sophisticated English?, Martine Ceberio, Christian Servin, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

Instructors from English department praise our students when they use the most sophisticated grammatical constructions and the most appropriate (often rarely used) words -- as long as this helps better convey all the subtleties of the meaning. On the other hand, we usually teach the students to use the most primitive Basic English when writing our papers -- this way, the resulting paper will be most accessible to the international audience. Who is right? In this paper, we analyze this question by using a natural model -- inspired by Zipf's law -- and we conclude that to achieve the largest …

Recommender Systems Using Cloud Technology, Gent Jashari

Theses and Dissertations

Ueb aplikacionet që ofrojnë sistemet e rekomanduara tani më janë bërë trend që çdo uebfaqe t’i ketë në mënyrë që ta tërheqin përdoruesin dhe “mos ta lejojnë atë që të kalojë pa e klikuar sugjerimin e rekomanduar”. Kjo është arritur duke përdorur teknika të ndryshme si: Collaborative filtering, Content-Based filtering dhe Hybrid filtering, ku kjo e fundit ndihmon për tejkalimin e sfidave që na shfaqen në sistemet e rekomanduara.

Përdorimin e cloud shërbimeve na ofrojnë shumë kompani mirëpo ndër ato më të njohurat janë: Microsoft Azure, Amazon Web Services dhe Google Cloud. Studimet e shumta tregojnë që për të krijuar …

Limitations Of Transformers On Clinical Text Classification, Shang Gao, Mohammed Alawad, Michael Todd Young, John Gounley, Noah Schaefferkoetter, Hong-Jun Yoon, Xiao-Cheng Wu, Eric B. Durbin, Jennifer Doherty, Antoinette Stroup, Linda Coyle, Georgia D. Tourassi

Kentucky Cancer Registry Faculty Publications

Bidirectional Encoder Representations from Transformers (BERT) and BERT-based approaches are the current state-of-the-art in many natural language processing (NLP) tasks; however, their application to document classification on long clinical texts is limited. In this work, we introduce four methods to scale BERT, which by default can only handle input sequences up to approximately 400 words long, to perform document classification on clinical texts several thousand words long. We compare these methods against two much simpler architectures -- a word-level convolutional neural network and a hierarchical self-attention network -- and show that BERT often cannot beat these simpler baselines when classifying …

Google Books, Jody Condit Fagan

Libraries

Google Books’ (GB) full-text search of more than 40 million books offers significant value for libraries and their patrons. However, Google’s refusal to disclose information about the coverage of GB, as well as observed gaps and inaccuracies in the collection and its metadata, makes it difficult to recommend with confidence for a given research need. While most search and retrieval functions work well, glitches aren’t hard to find, which suggests GB development is focused on user experiences that relate to monetization. Privacy and equity concerns surrounding GB mirror those of other big technology platforms. Still, every librarian should familiarize themselves …

Noise Annoyance In The Uae: A Twitter Case Study Via A Data-Mining Approach, Andrew Peplow, Justin Thomas, Aamna Alshehhi

All Works

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. Noise pollution is a growing global public health concern. Among other issues, it has been linked with sleep disturbance, hearing functionality, increased blood pressure and heart disease. Individuals are increasingly using social media to express complaints and concerns about problematic noise sources. This behavior—using social media to post noise-related concerns—might help us better identify troublesome noise pollution hotspots, thereby enabling us to take corrective action. The present work is a concept case study exploring the use of social media data as a means of identifying and monitoring noise annoyance across the …

Why Romans Sometimes Wrote 8 As Viii, And Sometimes As Iix: A Possible Explanation, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

Most of us are familiar with Roman numerals and with the standard way of describing numbers in the form of these numerals. What many people do not realize is that the actual ancient Romans often deviated from these rules. For example, instead of always writing the number 8 as VIII, i.e., 5 + 3, they sometimes wrote it as IIX, i.e., as 10 − 2. Some of such differences can be explained: e.g., the unusual way of writing 98 as IIC, i.e., as 100 − 2, can be explained by the fact that the Latin word for 98 literally means …

Speech Enhancement Using Speech Synthesis Techniques, Soumi Maiti

Dissertations, Theses, and Capstone Projects

Traditional speech enhancement systems reduce noise by modifying the noisy signal to make it more like a clean signal, which suffers from two problems: under-suppression of noise and over-suppression of speech. These problems create distortions in enhanced speech and hurt the quality of the enhanced signal. We propose to utilize speech synthesis techniques for a higher quality speech enhancement system. Synthesizing clean speech based on the noisy signal could produce outputs that are both noise-free and high quality. We first show that we can replace the noisy speech with its clean resynthesis from a previously recorded clean speech dictionary from …

Factors Influencing Small Construction Businesses From Implementing Information Security: A Case Study, Carl Andrew Mayes

Doctoral Dissertations and Projects

This qualitative study described the influence of small businesses’ failure to properly implement information security technologies resulting in the loss of sensitive and proprietary business information. A collective case study approach was used to determine the most effective way to gain a holistic picture of how small construction businesses make security technology implementation decisions to support their workforce. The theory guiding this study was the Unified Theory of Acceptance and Use of Technology (UTAUT) model which is related to the Theory of Planned Behavior and the Technology Acceptance Model which helped explain the intentions of individuals to use information systems. …

Treecaps: Tree-Based Capsule Networks For Source Code Processing, Duy Quoc Nghi Bui, Yijun Yu, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Recently program learning techniques have been proposed to process source code based on syntactical structures (e.g., Abstract Syntax Trees) and/or semantic information (e.g., Dependency Graphs). While graphs may be better at capturing various viewpoints of code semantics than trees, constructing graph inputs from code need static code semantic analysis that may not be accurate and introduces noise during learning. On the other hand, syntax trees are precisely defined according to the language grammar and easier to construct and process than graphs. We propose a new tree-based learning technique, named TreeCaps, by fusing capsule networks with tree-based convolutional neural networks, to …

Evidence Aware Neural Pornographic Text Identification For Child Protection, Kaisong Song, Yangyang Kang, Wei Gao, Zhe Gao, Changlong Sun, Xiaozhong Liu

Research Collection School Of Computing and Information Systems

Identifying pornographic text online is practically useful to protect children from access to such adult content. However, some authors may intentionally avoid using sensitive words in their pornographic texts to take advantage of the lack of human audits. Without prior knowledge guidance, real semantics of such pornographic text is difficult to understand by existing methods due to its high context-sensitivity and heavy usage of figurative language, which brings huge challenges to the porn detection systems used in social media platforms. In this paper, we approach to the problem as a document-level porn identification task by locating and integrating sentence-level evidence …

Decision-Guided Weighted Automata Extraction From Recurrent Neural Networks, Xiyue Zhang, Xiaoning Du, Xiaofei Xie, Lei Ma, Yang Liu, Meng Sun

Research Collection School Of Computing and Information Systems

Recurrent Neural Networks (RNNs) have demonstrated their effectiveness in learning and processing sequential data (e.g., speech and natural language). However, due to the black-box nature of neural networks, understanding the decision logic of RNNs is quite challenging. Some recent progress has been made to approximate the behavior of an RNN by weighted automata. They provide better interpretability, but still suffer from poor scalability. In this paper, we propose a novel approach to extracting weighted automata with the guidance of a target RNN’s decision and context information. In particular, we identify the patterns of RNN’s step-wise predictive decisions to instruct the …

Delineating Knowledge Domains In Scientific Domains In Scientific Literature Using Machine Learning (Ml), Abhay Maurya, Smarajit Paul Choudhury Mr., Kshitij Jaiswal Mr.

Library Philosophy and Practice (e-journal)

The recent years have witnessed an upsurge in the number of published documents. Organizations are showing an increased interest in text classification for effective use of the information. Manual procedures for text classification can be fruitful for a handful of documents, but the same lack in credibility when the number of documents increases besides being laborious and time-consuming. Text mining techniques facilitate assigning text strings to categories rendering the process of classification fast, accurate, and hence reliable. This paper classifies chemistry documents using machine learning and statistical methods. The procedure of text classification has been described in chronological order like …

Multi-Modal Classification Using Images And Text, Stuart J. Miller, Justin Howard, Paul Adams, Mel Schwan, Robert Slater

SMU Data Science Review

This paper proposes a method for the integration of natural language understanding in image classification to improve classification accuracy by making use of associated metadata. Traditionally, only image features have been used in the classification process; however, metadata accompanies images from many sources. This study implemented a multi-modal image classification model that combines convolutional methods with natural language understanding of descriptions, titles, and tags to improve image classification. The novelty of this approach was to learn from additional external features associated with the images using natural language understanding with transfer learning. It was found that the combination of ResNet-50 image …

Exploiting Bert And Roberta To Improve Performance For Aspect Based Sentiment Analysis, Gagan Reddy Narayanaswamy

Dissertations

Sentiment Analysis also known as opinion mining is a type of text research that analyses people’s opinions expressed in written language. Sentiment analysis brings together various research areas such as Natural Language Processing (NLP), Data Mining, and Text Mining, and is fast becoming of major importance to companies and organizations as it is started to incorporate online commerce data for analysis. Often the data on which sentiment analysis is performed will be reviews. The data can range from reviews of a small product to a big multinational corporation. The goal of performing sentiment analysis is to extract information from those …

Combination Of Facebook Prophet And Attention-Based Lstm With Multi- Source Data For Indian Stock Market Prediction, Pavan Nagesh

Dissertations

The stock market prediction has been the subject of interest to various researchers and analysts due to its highly unpredictable nature and serves as a perfect example for time series forecasting. Over the years deep learning models such as Long-Term Short-Term Memory and statistical models such as Autoregressive Integrated Moving Average have shown promising results in predicting future stock prices. But the results from these models cannot be generalized as they fail to incorporate the dynamics of the market and influence of several external factors such as political, social, investor's emotion, etc on stock markets. Recently Facebook’s creation of the …

Finetuning Bert And Xlnet For Sentiment Analysis Of Stock Market Tweets Using Mixout And Dropout Regularization, Shubham Jangir

Dissertations

Sentiment analysis is also known as Opinion mining or emotional mining which aims to identify the way in which sentiments are expressed in text and written data. Sentiment analysis combines different study areas such as Natural Language Processing (NLP), Data Mining, and Text Mining, and is quickly becoming a key concern for businesses and organizations, especially as online commerce data is being used for analysis. Twitter is also becoming a popular microblogging and social networking platform today for information among people as they contribute their opinions, thoughts, and attitudes on social media platforms over the years. Because of the large …

Complex Interactions Between Multiple Goal Operations In Agent Goal Management, Sravya Kondrakunta

Browse all Theses and Dissertations

A significant issue in cognitive systems research is to make an agent formulate and manage its own goals. Some cognitive scientists have implemented several goal operations to support this issue, but no one has implemented more than a couple of goal operations within a single agent. One of the reasons for this limitation is the lack of knowledge about how various goals operations interact with one another. This thesis addresses this knowledge gap by implementing multiple-goal operations, including goal formulation, goal change, goal selection, and designing an algorithm to manage any positive or negative interaction between them. These are integrated …

Complex Interactions Between Multiple Goal Operations In Agent Goal Management, Sravya Kondrakunta

Browse all Theses and Dissertations

A significant issue in cognitive systems research is to make an agent formulate and manage its own goals. Some cognitive scientists have implemented several goal operations to support this issue, but no one has implemented more than a couple of goal operations within a single agent. One of the reasons for this limitation is the lack of knowledge about how various goals operations interact with one another. This thesis addresses this knowledge gap by implementing multiple-goal operations, including goal formulation, goal change, goal selection, and designing an algorithm to manage any positive or negative interaction between them. These are integrated …

Incremental Unit Networks For Multimodal, Fine-Grained Information State Representation, Casey Kennington, David Schlangen

Computer Science Faculty Publications and Presentations

We offer a sketch of a fine-grained information state annotation scheme that follows directly from the Incremental Unit abstract model of dialogue processing when used within a multimodal, co-located, interactive setting. We explain the Incremental Unit model and give an example application using the Localized Narratives dataset, then offer avenues for future research.

Contextual Understanding Of Sequential Data Across Multiple Modalities, Sangwoo Cho

Electronic Theses and Dissertations, 2020-2023

In recent years, progress in computing and networking has made it possible to collect large volumes of data for various different applications in data mining and data analytics using machine learning methods. Data may come from different sources and in different shapes and forms depending on their inherent nature and the acquisition process. In this dissertation, we focus specifically on sequential data, which have been exponentially growing in recent years on platforms such as YouTube, social media, news agency sites, and other platforms. An important characteristic of sequential data is the inherent causal structure with latent patterns that can be …

Spectral And Latent Representation Distortion For Tts Evaluation, Thananchai Kongthaworn

Chulalongkorn University Theses and Dissertations (Chula ETD)

One of the main problems in the development of text-to-speech (TTS) systems is its reliance on subjective measures, typically the Mean Opinion Score (MOS). MOS requires a large number of people to reliably rate each utterance, making the development process slow and expensive. Recent research on speech quality assessment tends to focus on training models to estimate MOS, which requires a large number of training data, something that might not be available in low-resource languages. We propose an objective assessment metric based on the DTW distance using the spectrogram and the high-level features from an Automatic Speech Recognition (ASR) model …

An Ensemble Approach For Annotating Source Code Identifiers With Part-Of-Speech Tags, Christian D. Newman,, Michael J. Decker, Reem S. Alsuhaibani, Anthony Peruma, Mohamed Wiem Mkaouer, Satyajit Mohapatra, Tejal Vishnoi, Marcos Zampieri, Timothy Sheldon, Emily Hill

Articles

This paper presents an ensemble part-of-speech tagging approach for source code identifiers. Ensemble tagging is a technique that uses machine-learning and the output from multiple part-of-speech taggers to annotate natural language text at a higher quality than the part-of-speech taggers are able to obtain independently. Our ensemble uses three state-of-the-art part-of-speech taggers: SWUM, POSSE, and Stanford. We study the quality of the ensemble's annotations on five different types of identifier names: function, class, attribute, parameter, and declaration statement at the level of both individual words and full identifier names. We also study and discuss the weaknesses of our tagger to …

An Analysis Of People’S Reasoning For Sharing Real And Fake News, Anu Shrestha, Francesca Spezzano

Computer Science Faculty Publications and Presentations

The problem of the increase in the volume of fake news and its widespread over social media has gained massive attention as most of the population seeks social media for daily news diet. Humans are equally responsible for the surge of fake news spread. Thus, it is imperative to understand people’s behavior when they decide to share real and fake news items on social media. In an attempt to do so, we performed an analysis on data collected through a survey where participants (n= 363) were asked whether they were willing to share the given news item on their social …

การสร้างความต้องการเชิงฟังก์ชันและที่ไม่ใช่เชิงฟังก์ชันของซอฟต์แวร์จากการจำแนกบทวิจารณ์ของผู้ใช้งานโมไบล์แอปพลิเคชัน, ธนัชชา พันธ์ธรรม

Chulalongkorn University Theses and Dissertations (Chula ETD)

บทวิจารณ์ของผู้ใช้งานเป็นแหล่งข้อมูลที่สำคัญสำหรับนักพัฒนาโมไบล์แอปพลิเคชัน เพื่อใช้ในการปรับปรุงและวิวัฒนาการแอปพลิเคชันหลังจากที่ได้ปล่อยให้ใช้งานไปแล้ว เนื่องจากข้อมูลบทวิจารณ์ของผู้ใช้งานมีจำนวนมากจึงเป็นเรื่องยุ่งยากสำหรับทีมนักพัฒนาโมไบล์แอปพลิเคชันที่จะระบุว่าบทวิจารณ์ของผู้ใช้งานใดประกอบไปด้วยข้อมูลที่เป็นประโยชน์ต่อการปรับปรุงและวิวัฒนาการโมไบล์แอปพลิเคชันเพิ่มเติม วิทยานิพนธ์นี้นำเสนอความพยายามที่จะอำนวยความสะดวกให้แก่ทีมนักพัฒนาในขั้นต้นด้วยการสร้างความต้องการเชิงฟังก์ชันและที่ไม่ใช่เชิงฟังก์ชันโดยอัตโนมัติจากข้อมูลบทวิจารณ์ของผู้ใช้งานโมไบล์แอปพลิเคชันบนแอปสโตร์และเพลย์สโตร์ แนวทางที่นำเสนอประกอบด้วยสามขั้นตอน เริ่มจากการใช้อัลกอริทึมการจำแนกข้อความเพื่อจำแนกบทวิจารณ์ของผู้ใช้งานออกเป็นบทวิจารณ์ของผู้ใช้งานเชิงฟังก์ชันหรือที่ไม่ใช่เชิงฟังก์ชัน ขั้นตอนที่สองบทวิจารณ์ของผู้ใช้งานที่ไม่ซ้ำกันจะถูกระบุโดยใช้เทคนิคการจัดกลุ่มและการวิเคราะห์ความคล้ายคลึงกันของข้อความ ในขั้นตอนสุดท้ายข้อมูลที่มีความสำคัญจะถูกสกัดจากบทวิจารณ์ของผู้ใช้งานเพื่อใช้สร้างความต้องการเชิงฟังก์ชันและที่ไม่ใช่เชิงฟังก์ชันโดยใช้แบบรูปข้อมูลบทวิจารณ์ของผู้ใช้งานและแม่แบบความต้องการ ในส่วนของการประเมินผล ความต้องการที่ถูกสร้างขึ้นจากแนวทางที่นำเสนอได้รับคะแนนต่ำถึงสูงแตกต่างกันไปในแง่ของความสามารถในการอ่านได้ง่าย ความไม่กำกวม ความสมบูรณ์ และความสมเหตุสมผล ซึ่งแนวทางที่วิทยานิพนธ์นำเสนอนี้สามารถช่วยทีมนักพัฒนาระบุถึงความต้องการการเปลี่ยนแปลงทั้งในเชิงฟังก์ชันและที่ไม่ใช่เชิงฟังก์ชันจากเสียงสะท้อนโดยตรงของผู้ใช้งานซึ่งควรได้รับการพิจารณาเพื่อใช้ในการปรับปรุงและวิวัฒนาการโมไบล์แอปพลิเคชันต่อไป