Digital Commons Network^™

Do Pre-Trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation And A Reasonable Approach, Xin Lv, Yankai Lin, Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu, Peng Li, Jie Zhou

Research Collection School Of Computing and Information Systems

In recent years, pre-trained language models (PLMs) have been shown to capture factual knowledge from massive texts, which encourages the proposal of PLM-based knowledge graph completion (KGC) models. However, these models are still quite behind the SOTA KGC models in terms of performance. In this work, we find two main reasons for the weak performance: (1) Inaccurate evaluation setting. The evaluation setting under the closed-world assumption (CWA) may underestimate the PLM-based KGC models since they introduce more external knowledge; (2) Inappropriate utilization of PLMs. Most PLM-based KGC models simply splice the labels of entities and relations as inputs, leading to …

On The Transferability Of Pre-Trained Language Models For Low-Resource Programming Languages, Fuxiang Chen, Fatemeh H. Fard, David Lo, Timofey Bryksin

Research Collection School Of Computing and Information Systems

A recent study by Ahmed and Devanbu reported that using a corpus of code written in multilingual datasets to fine-tune multilingual Pre-trained Language Models (PLMs) achieves higher performance as opposed to using a corpus of code written in just one programming language. However, no analysis was made with respect to fine-tuning monolingual PLMs. Furthermore, some programming languages are inherently different and code written in one language usually cannot be interchanged with the others, i.e., Ruby and Java code possess very different structure. To better understand how monolingual and multilingual PLMs affect different programming languages, we investigate 1) the performance of …

Gr-196 - Automatically Improve Writing For Research Papers Using Transformer Based Deep Learning, Srivarna Settisara Janney

C-Day Computing Showcase

Research papers are generally required to be written in English. It is quite a challenge for non-English speaking researchers to write high quality research papers. Our research focuses on designing, implementing and experimenting with novel transformer based deep learning strategies that can automatically improve the quality of writing for research papers in different domains.

Beyond Hcahps: Analysis Of Patients’ Comments Provides An Expanded View Of Their Hospital Experiences, Andrew S. Gallan, Rakesh Niraj, Awanindra Singh

Patient Experience Journal

An important concern for health care professionals is that standardized patient surveys may not fully capture all the topics that are important to patients. As a result, health care professionals may not have a complete picture of what their patients experience. The purpose of this research is to utilize a state-of-the-art Natural Language Processing technique to make sense of patients’ solicited, unstructured comments to gain a deeper and broader understanding of their experiences in the hospital. We analyzed a large dataset of inpatient survey responses (48,592 patients generating 65,998 comments) by a patient experience survey vendor for an eleven-hospital health …

Impact Of Traditional Versus Alternative Assessment On Student Achievement, Beth Lustgarten

Honors Projects

The focus of this study looks at the effect of alternative assessment on student achievement in a high school science classroom. Within this action research, students have choices and are able to demonstrate creativity in their alternative assessments. By comparing student results from traditional and alternative assessments, the impact of assessment showed students had an overwhelming preference for completing alternative assessments, and a majority of students did better on the alternative assessment when compared to the traditional assessment.

Cancel Culture: Who Or What Will Be Next?, Christine Trumper

Honors Projects in Data Science

This paper utilizes Data Science and Applied Statistic techniques, to perform an analytical dive into Cancel Culture as it is referenced and used on Twitter. The research focuses on analyzing how Cancel Culture has affected the sentiment of Twitter, specifically how it impacts prominent topics in the media that have occurred between February 2021 to September 2021. The development of a topic and sentiment analysis will be based on 1,302,844 Tweets collected using Twitter’s API. Cancel Culture became popularized on social media in the past few years and there is little concrete information regarding its process and the demographics it …

Annual Faculty Research Symposium 2022, Oakwood University

Proceedings

No abstract provided.

Cross-Temporal Snapshot Alignment For Dynamic Multi-Relational Networks, Lvjia Chen, Shangsong Liang

Machine Learning Faculty Publications

A dynamic network is often represented as a sequence of snapshots evolving over time. In certain real-world scenarios, the identities of nodes in snapshots of a dynamic network are unknown and need to be figured out. To deal with such a challenge, recently, the task of cross-temporal snapshot alignment for dynamic networks is proposed, which aims to match equivalent nodes across temporal snapshots of a dynamic network given a small set of identified nodes. However, in many dynamic multi-relational networks like temporal knowledge graphs, the relation type information of edges, which can be useful for the alignment task, is neglected …

Applied Math In Introductory Chemistry, Ji Kim, Grace Pai

Open Educational Resources

Students, particularly those who are non-science majors, often struggle with college-level science courses required for graduation due to the applied mathematics needed to successfully complete the course. This resource includes four activities on the topics of units and measurements, dimensional analysis, density, and gases. These topics were specifically designed to teach the mathematics embedded in these topics in a culturally responsive way. Throughout the activities, we incorporate these four elements of culturally relevant pedagogy (Ladson-Billings, 2009) in order to engage students in successfully solving basic mathematics in chemistry while promoting their interest in learning chemistry.

Mucot: Multilingual Contrastive Training For Question-Answering In Low-Resource Languages, Gokul Karthik Kumar, Abhishek Singh Gehlot, Sahal Shaji Mullappilly, Karthik Nandakumar

Computer Vision Faculty Publications

Accuracy of English-language Question Answering (QA) systems has improved significantly in recent years with the advent of Transformer-based models (e.g., BERT). These models are pre-trained in a self-supervised fashion with a large English text corpus and further fine-tuned with a massive English QA dataset (e.g., SQuAD). However, QA datasets on such a scale are not available for most of the other languages. Multi-lingual BERT-based models (mBERT) are often used to transfer knowledge from high-resource languages to low-resource languages. Since these models are pre-trained with huge text corpora containing multiple languages, they typically learn language-agnostic embeddings for tokens from different languages. …

Improving Negation Detection With Negation-Focused Pre-Training, Hung Thinh Truong, Timothy Baldwin, Trevor Cohn, Karin Verspoor

Natural Language Processing Faculty Publications

Negation is a common linguistic feature that is crucial in many language understanding tasks, yet it remains a hard problem due to diversity in its expression in different types of text. Recent work has shown that state-of-the-art NLP models underperform on samples containing negation in various tasks, and that negation detection models do not transfer well across domains. We propose a new negation-focused pre-training strategy, involving targeted data augmentation and negation masking, to better incorporate negation information into language models. Extensive experiments on common benchmarks show that our proposed approach improves negation detection performance and generalizability over the strong baseline …

Considering The Context To Build Theory In Hci, Hri, And Hmc: Explicating Differences In Processes Of Communication And Socialization With Social Technologies, Andrew Gambino, Bingjie Liu

Human-Machine Communication

The proliferation and integration of social technologies has occurred quickly, and the specific technologies with which we engage are ever-changing. The dynamic nature of the development and use of social technologies is often acknowledged by researchers as a limitation. In this manuscript, however, we present a discussion on the implications of our modern technological context by focusing on processes of socialization and communication that are fundamentally different from their interpersonal corollary. These are presented and discussed with the goal of providing theoretical building blocks toward a more robust understanding of phenomena of human-computer interaction, human-robot interaction, human-machine communication, and interpersonal …

Toward Suicidal Ideation Detection With Lexical Network Features And Machine Learning, Ulya Bayram, William Lee, Daniel Santel, Ali Minai, Peggy Clark, Tracy Glauser, John Pestian

Northeast Journal of Complex Systems (NEJCS)

In this study, we introduce a new network feature for detecting suicidal ideation from clinical texts and conduct various additional experiments to enrich the state of knowledge. We evaluate statistical features with and without stopwords, use lexical networks for feature extraction and classification, and compare the results with standard machine learning methods using a logistic classifier, a neural network, and a deep learning method. We utilize three text collections. The first two contain transcriptions of interviews conducted by experts with suicidal (n=161 patients that experienced severe ideation) and control subjects (n=153). The third collection consists of interviews conducted by experts …

A Monte Carlo Analysis Of Seven Dichotomous Variable Confidence Interval Equations, Morgan Juanita Dubose

Masters Theses & Specialist Projects

Department of Psychological Sciences Western Kentucky University There are two options to estimate a range of likely values for the population mean of a continuous variable: one for when the population standard deviation is known and another for when the population standard deviation is unknown. There are seven proposed equations to calculate the confidence interval for the population mean of a dichotomous variable: normal approximation interval, Wilson interval, Jeffreys interval, Clopper-Pearson, Agresti-Coull, arcsine transformation, and logit transformation. In this study, I compared the percent effectiveness of each equation using a Monte Carlo analysis and the interval range over a range …

It Won’T Be Easy, Allison Arkush

School of Art, Art History, and Design: Theses and Student Creative Work

Interdisciplinary artist Allison Arkush engages a wide range of materials, modalities, and research in her practice. In It Won’t Be Easy, Arkush places and piles her multimedia sculptures throughout the gallery to create installations that overlap ­with her writing and poetry, sometimes layering in (or extending out to) audio and video components. This approach facilitates the probing exploration of prevailing value systems through a flattening of hierarchies among and between humans, the other-than-human, and the inanimate—though no less lively. Her work meditates on and ‘vendiagrams’ things forsaken and sacred, the traumatic and nostalgic. The exhibition title acknowledges that the …

Few-Shot Object Detection Via Baby Learning, Anh-Khoa Nguyen Vu, Nhat-Duy Nguyen, Khanh-Duy Nguyen, Vinh-Tiep Nguyen, Thanh Duc Ngo, Thanh-Toan Do, Tam Nguyen

Computer Science Faculty Publications

Few-shot learning is proposed to overcome the problem of scarce training data in novel classes. Recently, few-shot learning has been well adopted in various computer vision tasks such as object recognition and object detection. However, the state-of-the-art (SOTA) methods have less attention to effectively reuse the information from previous stages. In this paper, we propose a new framework of few-shot learning for object detection. In particular, we adopt Baby Learning mechanism along with the multiple receptive fields to effectively utilize the former knowledge in novel domain. The propoed framework imitates the learning process of a baby through visual cues. The …

On Explaining Multimodal Hateful Meme Detection Models, Ming Shan Hee, Roy Ka-Wei Lee, Wen Haw Chong

Research Collection School Of Computing and Information Systems

Hateful meme detection is a new multimodal task that has gained significant traction in academic and industry research communities. Recently, researchers have applied pre-trained visual-linguistic models to perform the multimodal classification task, and some of these solutions have yielded promising results. However, what these visual-linguistic models learn for the hateful meme classification task remains unclear. For instance, it is unclear if these models are able to capture the derogatory or slurs references in multimodality (i.e., image and text) of the hateful memes. To fill this research gap, this paper propose three research questions to improve our understanding of these visual-linguistic …

Victor: An Implicit Approach To Mitigate Misinformation Via Continuous Verification Reading, Kuan-Chieh Lo, Shih-Chieh Dai, Aiping Xiong, Jing Jiang, Lun-Wei Ku

Research Collection School Of Computing and Information Systems

We design and evaluate VICTOR, an easy-to-apply module on top of a recommender system to mitigate misinformation. VICTOR takes an elegant, implicit approach to deliver fake-news verifications, such that readers of fake news can continuously access more verified news articles about fake-news events without explicit correction. We frame fake-news intervention within VICTOR as a graph-based question-answering (QA) task, with Q as a fake-news article and A as the corresponding verified articles. Specifically, VICTOR adopts reinforcement learning: it first considers fake-news readers’ preferences supported by underlying news recommender systems and then directs their reading sequence towards the verified news articles. To …

Entity Based Sentiment Analysis For Textual Health Advice, Dae Lim Chung

Computer Science Senior Theses

This work explores entity based sentiment analysis for textual health advice through deep learning. We fine tuned a pretrained BERT model to analyze sentiments across five different predetermined categories which consist of food, medicine, disease, exercise, and vitality for three different sentiments: positive, negative, and neutral. Original set of annotated medical dataset from Dartmouth College’s Persist Lab was used to conduct the experiments. For the aim of tailoring the data for the purpose of entity based sentiment analysis, we explored data transformation techniques to generate optimum training examples. During the experiments, we were able to discover that the wide variety …

Trend: Temporal Event And Node Dynamics For Graph Representation Learning, Zhihao Wen, Yuan Fang

Research Collection School Of Computing and Information Systems

Temporal graph representation learning has drawn significant attention for the prevalence of temporal graphs in the real world. However, most existing works resort to taking discrete snapshots of the temporal graph, or are not inductive to deal with new nodes, or do not model the exciting effects which is the ability of events to influence the occurrence of another event. In this work, We propose TREND, a novel framework for temporal graph representation learning, driven by TempoRal Event and Node Dynamics and built upon a Hawkes process-based graph neural network (GNN). TREND presents a few major advantages: (1) it is …

User Satisfaction Estimation With Sequential Dialogue Act Modeling In Goal-Oriented Conversational Systems, Yang Deng, Wenxuan Zhang, Wai Lam, Hong Cheng, Helen Meng

Research Collection School Of Computing and Information Systems

User Satisfaction Estimation (USE) is an important yet challenging task in goal-oriented conversational systems. Whether the user is satisfied with the system largely depends on the fulfillment of the user’s needs, which can be implicitly reflected by users’ dialogue acts. However, existing studies often neglect the sequential transitions of dialogue act or rely heavily on annotated dialogue act labels when utilizing dialogue acts to facilitate USE. In this paper, we propose a novel framework, namely USDA, to incorporate the sequential dynamics of dialogue acts for predicting user satisfaction, by jointly learning User Satisfaction Estimation and Dialogue Act Recognition tasks. In …

Entity-Driven Fact-Aware Abstractive Summarization Of Biomedical Literature, Amanuel Alambo, Tanvi Banerjee, Krishnaprasad Thirunarayan, Michael Raymer

Computer Science and Engineering Faculty Publications

As part of the large number of scientific articles being published every year, the publication rate of biomedical literature has been increasing. Consequently, there has been considerable effort to harness and summarize the massive amount of biomedical research articles. While transformer-based encoder-decoder models in a vanilla source document-to-summary setting have been extensively studied for abstractive summarization in different domains, their major limitations continue to be entity hallucination (a phenomenon where generated summaries constitute entities not related to or present in source article(s)) and factual inconsistency. This problem is exacerbated in a biomedical setting where named entities and their semantics (which …

The Global Rise Of Online Devices, Cyber Crime And Cyber Defense: Enhancing Ethical Actions, Counter Measures, Cyber Strategy, And Approaches, Naresh Kshetri

Dissertations

The rise of online devices, online users, online shopping, online gaming, and online teaching has ultimately given rise to online attacks and online crimes. As cases of COVID-19 seem to increase day by day, so do online crimes and attacks (as many sectors and organizations went 100% online). Technological advancements and cyber warfare already generated many ethical issues, as internet users increasingly need ethical cyber defense strategies.

Individual internet users have challenges on their end; and on the other end, nation states (some secretly, some openly), are investing in robot weapons and autonomous weapons systems (AWS). New technologies have combined …

Vedantic Basis And Praxis Of The Integral Advaita Of Sri Aurobindo, Debashish Banerji

Monsoon: South Asian Studies Association Journal

The integral nondualism of Sri Aurobindo can be traced to the great pronouncements (mahāvākya) of the Upanishads and later commentaries. This study examines teachings on the Supermind (vijñāna) and the other four kinds of consciousness that define human reality: Matter (annaṃ), Life (prāṇaḥ), Mind (manaḥ), and Bliss (ānanda). Through Yoga and Tantra, one learns and embodies the pathway to the divine.

Digital And Spatial Humanities Mapping: Eurasia-Pacific Early Trade And Belief Linkages, Igor Sitnikov, David Blundell

Monsoon: South Asian Studies Association Journal

The Eurasia-Pacific is a dynamic region of rapid economic growth, cultural awareness, natural resource exploration, and military buildup. The concept of the region is relatively new, featuring contested vast areas of geo-resource space of numerous cultures and languages. The current findings in anthropology and archaeology and even its more specific subfields such as folklore are important contribution to the understanding of periodic environmental changes and technical innovations were the main forces of transformations in social structures that have determined the mechanisms and levels of cross-cultural trade activity across the region. We have traced early trade and belief linkages across Eurasia-Pacific …

Tusha Hiti: The Origin And Significance Of The Name, Deepak Shimkhada

Monsoon: South Asian Studies Association Journal

In this article, the author examines the royal bath called Tushā Hiti located in Sūndari Chowk (Beautiful Courtyard) of Pātan Durbar Square, using six different methods of investigation. The question: What is in a name? started the ball of investigation rolling and along the way were added more supporting blocks such as history, iconography, function and purpose, notion of purity and impurity, and finally the hiti in popular culture to get a complete picture of the subject in question.

Ganges In Indian Sculpture And Literature: Mythology And Personification, Nalini Rao

Monsoon: South Asian Studies Association Journal

The river Ganges is a symbol of wealth, purity and eternity, and its sacred waters have inspired sages, philosophers, and artists in India who have immortalized its divine imagery. However, it has rarely been understood from a historical point of view, as to how it became so sacred and to view it from a multi-dimensional and interdisciplinary perspective with an accumulation of layers of historical thought and practices, provides a rationale for the living practices around the river. The paper explores the evolution of the concept of sacredness and eternity of River Ganges through art- historical and archaeological evidence. It …

Diversity, Equity, And Inclusion: Perspectives From Contemporary India And 6th Century Jain Yoga, Christopher Key Chapple

Monsoon: South Asian Studies Association Journal

Times New Roman

Characteristics And Funding Strategies Of Mathematical Research, Xiaoxi Xiao, Xiaoshan Gao, Yaxiang Yuan

Bulletin of Chinese Academy of Sciences (Chinese Version)

Strengthening mathematical research aiming at the national strategic needs and major frontier problems is conducive to promoting mathematics research to play a more important strategic role in national development and international competition. This study analyzes the basic characteristics of mathematical research, summarizes the international experiences in funding mathematical research, and then deeply analyzes the major problems of Chinese funding mechanisms for mathematical research, such as the lack of overall planning, the short of sustainable and stable support, and the urgent need to improve the training, selecting, and funding mechanism for high-level mathematical talents. It also puts forward some policy suggestions, …

Symbolic Semantic Memory In Transformer Language Models, Robert Kenneth Morain

Theses and Dissertations

This paper demonstrates how transformer language models can be improved by giving them access to relevant structured data extracted from a knowledge base. The knowledge base preparation process and modifications to transformer models are explained. We evaluate these methods on language modeling and question answering tasks. These results show that even simple additional knowledge augmentation leads to a reduction in validation loss by 73%. These methods also significantly outperform common ways of improving language models such as increasing the model size or adding more data.