Digital Commons Network^™

Multi-Level Head-Wise Match And Aggregation In Transformer For Textual Sequence Matching, Shuohang Wang, Yunshi Lan, Yi Tay, Jing Jiang, Jingjing Liu

Research Collection School Of Computing and Information Systems

Transformer has been successfully applied to many natural language processing tasks. However, for textual sequence matching, simple matching between the representation of a pair of sequences might bring in unnecessary noise. In this paper, we propose a new approach to sequence pair matching with Transformer, by learning head-wise matching representations on multiple levels. Experiments show that our proposed approach can achieve new state-of-the-art performance on multiple tasks that rely only on pre-computed sequence-vectorrepresentation, such as SNLI, MNLI-match, MNLI-mismatch, QQP, and SQuAD-binary

Distinguishing Similar Design Pattern Instances Through Temporal Behavior Analysis, Renhao Xiong, David Lo, Bixin Li

Research Collection School Of Computing and Information Systems

Design patterns (DPs) encapsulate valuable design knowledge of object-oriented systems. Detecting DP instances helps to reveal the underlying rationale, thus facilitates the maintenance of legacy code. Resulting from the internal similarity of DPs, implementation variants, and missing roles, approaches based on static analysis are unable to well identify structurally similar instances. Existing approaches further employ dynamic techniques to test the runtime behaviors of candidate instances. Automatically verifying the runtime behaviors of DP instances is a challenging task in multiple aspects. This paper presents an approach to improve the verification process of existing approaches. To exercise the runtime behaviors of DP …

Essential Sentences For Navigating Stack Overflow Answers, Sarah Nadi, Christoph Treude

Research Collection School Of Computing and Information Systems

Stack Overflow (SO) has become an essential resource for software development. Despite its success and prevalence, navigating SO remains a challenge. Ideally, SO users could benefit from highlighted navigational cues that help them decide if an answer is relevant to their task and context. Such navigational cues could be in the form of essential sentences that help the searcher decide whether they want to read the answer or skip over it. In this paper, we compare four potential approaches for identifying essential sentences. We adopt two existing approaches and develop two new approaches based on the idea that contextual information …

Robust Neural Machine Translation, Abdul Rafae Khan

Dissertations, Theses, and Capstone Projects

This thesis aims for general robust Neural Machine Translation (NMT) that is agnostic to the test domain. NMT has achieved high quality on benchmarks with closed datasets such as WMT and NIST but can fail when the translation input contains noise due to, for example, mismatched domains or spelling errors. The standard solution is to apply domain adaptation or data augmentation to build a domain-dependent system. However, in real life, the input noise varies in a wide range of domains and types, which is unknown in the training phase. This thesis introduces five general approaches to improve NMT accuracy and …

Image Enhanced Event Detection In News Articles, Meihan Tong, Shuai Wang, Yixin Cao, Bin Xu, Juaizi Li, Lei Hou, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Event detection is a crucial and challenging sub-task of event extraction, which suffers from a severe ambiguity issue of trigger words. Existing works mainly focus on using textual context information, while there naturally exist many images accompanied by news articles that are yet to be explored. We believe that images not only reflect the core events of the text, but are also helpful for the disambiguation of trigger words. In this paper, we first contribute an image dataset supplement to ED benchmarks (i.e., ACE2005) for training and evaluation. We then propose a novel Dual Recurrent Multimodal Model, DRMM, to conduct …

Are The Code Snippets What We Are Searching For? A Benchmark And An Empirical Study On Code Search With Natural-Language Queries, Shuhan Yan, Hang Yu, Yuting Chen, Beijun Shen

Research Collection School Of Computing and Information Systems

Code search methods, especially those that allow programmers to raise queries in a natural language, plays an important role in software development. It helps to improve programmers' productivity by returning sample code snippets from the Internet and/or source-code repositories for their natural-language queries. Meanwhile, there are many code search methods in the literature that support natural-language queries. Difficulties exist in recognizing the strengths and weaknesses of each method and choosing the right one for different usage scenarios, because (1) the implementations of those methods and the datasets for evaluating them are usually not publicly available, and (2) some methods leverage …

Preface To The Special Issue On Advances In Argumentation In Artificial Intelligence, Pierpaolo Dondio, Luca Longo, Stefano Bistarelli

Articles

Now at the forefront of automated reasoning, argumentation has become a key research topic within Artificial Intelligence. It involves the investigation of those activities for the production and exchange of arguments, where arguments are attempts to persuade someone of something by giving reasons for accepting a particular conclusion or claim as evident. The study of argumentation has been the focus of attention of philosophers and scholars, from Aristotle and classical rhetoric to the present day. The computational study of arguments has emerged as a field of research in AI in the last two decades, mainly fuelled by the interest from …

Harnessing Artificial Intelligence Capabilities To Improve Cybersecurity, Sherali Zeadally, Erwin Adi, Zubair Baig, Imran A. Khan

Information Science Faculty Publications

Cybersecurity is a fast-evolving discipline that is always in the news over the last decade, as the number of threats rises and cybercriminals constantly endeavor to stay a step ahead of law enforcement. Over the years, although the original motives for carrying out cyberattacks largely remain unchanged, cybercriminals have become increasingly sophisticated with their techniques. Traditional cybersecurity solutions are becoming inadequate at detecting and mitigating emerging cyberattacks. Advances in cryptographic and Artificial Intelligence (AI) techniques (in particular, machine learning and deep learning) show promise in enabling cybersecurity experts to counter the ever-evolving threat posed by adversaries. Here, we explore AI's …

In Their Shoes: A Structured Analysis Of Job Demands, Resources, Work Experiences, And Platform Commitment Of Crowdworkers In China, Yihong Wang, Konstantinos Papangelis, Ioanna Lykourentzou, Hai-Ning Liang, Irwyn Sadien, Evangelia Demerouti, Vassilis-Javed Khan

Articles

Despite the growing interest in crowdsourcing, this new labor model has recently received severe criticism. The most important point of this criticism is that crowdworkers are often underpaid and overworked. This severely affects job satisfaction and productivity. Although there is a growing body of evidence exploring the work experiences of crowdworkers in various countries, there have been a very limited number of studies to the best of our knowledge exploring the work experiences of Chinese crowdworkers. In this paper we aim to address this gap. Based on a framework of well-established approaches, namely the Job Demands-Resources model, the Work Design …

Interpretability Of Api Call Topic Models: An Exploratory Study, Puntitra Glendowne, Dae Glendowne

Faculty Publications

Topic modeling is an unsupervised method for discovering semantically coherent combinations of words, called topics, in unstructured text. However, the human interpretability of topics discovered from non-natural language corpora, specifically Windows API call logs, is unknown. Our objective is to explore the coherence of topics and their ability to represent the themes of API calls from malware analysts’ perspective. Three Latent Dirichlet Allocation (LDA) models were fit to a collection of dynamic API call logs. Topics, or behavioral themes, were manually evaluated by malware analysts. The results were compared to existing automated quality measures. Participants were able to accurately determine …

Expectations Of Artificial Intelligence And The Performativity Of Ethics: Implications For Communication Governance, Aphra Kerr, Marguerite Barry, John D. Kelleher

Articles

This article draws on the sociology of expectations to examine the construction of expectations of ‘ethical AI’ and considers the implications of these expectations for communication governance. We first analyse a range of public documents to identify the key actors, mechanisms and issues which structure societal expectations around artificial intelligence (AI) and an emerging discourse on ethics. We then explore expectations of AI and ethics through a survey of members of the public. Finally, we discuss the implications of our findings for the role of AI in communication gover- nance. We find that, despite societal expectations that we can design …

Development And Field Testing Of A Narrative-Centered Digital Game For English Comprehension, Jenilyn Agapito, Dominique Marie Antoinette Manahan, Ma. Monica L. Moreno, Jose Isidro Beraquit, Ingrid Yvonne Herras, Kevin Arnel C. Mora, Johanna Marion R. Torres, Ma. Mercedes T. Rodrigo

Education Department Faculty Publications

This paper describes the development and field testing of Learning Likha: Rangers to the Rescue, a narrative-centered, mobile-based digital game for practicing English comprehension. Twenty-seven (27) student participants from Grades 4, 5, and 6 were invited to play the game and answer a comprehension test to determine their level of understanding of the game’s contents. Self-report questionnaires were also used to assess the extent to which they enjoyed playing the game. Three (3) teachers were likewise invited for a focus group discussion (FGD) to gather their insights about the game and how they may use it in their classes. Student’s …

An Evaluation Of Text Representation Techniques For Fake News Detection Using: Tf-Idf, Word Embeddings, Sentence Embeddings With Linear Support Vector Machine., Sangita Sriram

Dissertations

In a world where anybody can share their views, opinions and make it sound like these are facts about the current situation of the world, Fake News poses a huge threat especially to the reputation of people with high stature and to organizations. In the political world, this could lead to opposition parties making use of this opportunity to gain popularity in their elections. In the medical world, a fake scandalous message about a medicine giving side effects, hospital treatment gone wrong or even a false message against a practicing doctor could become a big menace to everyone involved in …

Using Natural Language Processing To Categorize Fictional Literature In An Unsupervised Manner, Dalton J. Crutchfield

Electronic Theses and Dissertations

When following a plot in a story, categorization is something that humans do without even thinking; whether this is simple classification like “This is science fiction” or more complex trope recognition like recognizing a Chekhov's gun or a rags to riches storyline, humans group stories with other similar stories. Research has been done to categorize basic plots and acknowledge common story tropes on the literary side, however, there is not a formula or set way to determine these plots in a story line automatically. This paper explores multiple natural language processing techniques in an attempt to automatically compare and cluster …

Automated Change Detection In Privacy Policies, Andrick Adhikari

Electronic Theses and Dissertations

Privacy policies notify Internet users about the privacy practices of websites, mobile apps, and other products and services. However, users rarely read them and struggle to understand their contents. Also, the entities that provide these policies are sometimes unmotivated to make them comprehensible. Due to the complicated nature of these documents, it gets even harder for users to understand and take note of any changes of interest or concern when these policies are changed or revised.

With recent development of machine learning and natural language processing, tools that can automatically annotate sentences of policies have been developed. These annotations can …

Kidspell: A Child-Oriented, Rule-Based, Phonetic Spellchecker, Brody Downs, Oghenemaro Anuyah, Aprajita Shukla, Jerry Alan Fails, Maria Soledad Pera, Katherine Wright, Casey Kennington

Computer Science Faculty Publications and Presentations

For help with their spelling errors, children often turn to spellcheckers integrated in software applications like word processors and search engines. However, existing spellcheckers are usually tuned to the needs of traditional users (i.e., adults) and generally prove unsatisfactory for children. Motivated by this issue, we introduce KidSpell, an English spellchecker oriented to the spelling needs of children. KidSpell applies (i) an encoding strategy for mapping both misspelled words and spelling suggestions to their phonetic keys and (ii) a selection process that prioritizes candidate spelling suggestions that closely align with the misspelled word based on their respective keys. To assess …

A Description Of A Humans Knowledge Using Artificial Intelligence, Dj Price

Mahurin Honors College Capstone Experience/Thesis Projects

There currently does not exist a way to easily view the relationships between a collection of written items (e.g. sports articles, diary entries, research papers). In recent years, novel machine learning methods have been developed which are very good at extracting semantic relationships from large numbers of documents. One of them is the (unsupervised) machine learning model Doc2Vec which constructs vectors for documents. The research project detailed in this paper uses this and other already existing algorithms to analyze the relationship between pieces of text. We set forth a broader ambition for this project before discussing the use and need …

Social Media Based Algorithmic Clinical Decision Support Learning From Behavioral Predispositions, Radhika V. Medury

Doctoral Dissertations

Behavioral disorders are disabilities characterized by an individual’s mood, thinking, and social interactions. The commonality of behavioral disorders amongst the United States population has increased in the last few years, with an estimated 50% of all Americans diagnosed with a behavioral disorder at some point in their lifetime. AttentionDeficit/Hyperactivity Disorder is one such behavioral disorder that is a severe public health concern because of its high prevalence, incurable nature, significant impact on domestic life, and peer relationships. Symptomatically, in theory, ADHD is characterized by inattention, hyperactivity, and impulsivity. Access to providers who can offer diagnosis and treat the disorder varies …

Automatic Distinction Between Twitter Bots And Humans, Jeremiah Stubbs

All Undergraduate Theses and Capstone Projects

Weak artificial intelligence uses encoded functions of rules to process information. This kind of intelligence is competent, but lacks consciousness, and therefore cannot comprehend what it is doing. In another view, strong artificial intelligence has a mind of its own that resembles a human mind. Many of the bots on Twitter are only following a set of encoded rules. Previous studies have created machine learning algorithms to determine whether a Twitter account was being run by a human or a bot. Twitter bots are improving and some are even fooling humans. Creating a machine learning algorithm that differentiates a bot …

Learning Context-Sensitive Human Emotions In Categorical And Dimensional Domains, Pooyan Balouchian

Electronic Theses and Dissertations, 2020-2023

Still image emotion recognition (ER) has been receiving increasing attention in recent years due to the tremendous amount of social media content on the Web. Many works offer both categorical and dimensional methods to detect image sentiments, while others focus on extracting the true social signals, such as happiness and anger. Deep learning architectures have delivered great suc- cess, however, their dependency on large-scale datasets labeled with (1) emotion, and (2) valence, arousal and dominance, in categorical and dimensional domains respectively, introduce challenges the community tries to tackle. Emotions offer dissimilar semantics when aroused in different con- texts, however "context-sensitive" …

Local Alignment Of Frame Of Reference Assignment In English And Swedish Dialogue, Simon Dobnik, John D. Kelleher, Christine Howes

Conference papers

In this paper we examine how people assign, interpret, negotiate and repair the frame of reference (FoR) in online text-based dialogues discussing spatial scenes in English and Swedish. We describe our corpus and data collection which involves a coordination experiment in which dyadic dialogue participants have to identify differences in their picture of a visual scene. As their perspectives of the scene are different, they must coordinate their FoRs in order to complete the task. Results show that participants do not align on a global FoR, but tend to align locally, for sub-portions (or particular conversational games) in the dialogue. …

Special Topics In Natural Language Processing: Mwe Identification, Opinion Question Answering And Summarization, Aishwarya Ashok

Computer Science and Engineering Dissertations - Archive

Natural Language Processing (NLP) is the use of computers for the analysis of text. The approaches used to solve problems in NLP has transitioned from human tagging to statistical methods and currently many of the approaches make use of techniques from Machine Learning (ML) and Artificial Intelligence (AI). Some of the text-based problems in NLP include question answering, summarization, and text-based recommendation systems. The amount of text data that is available is increasing by the day. With the growing size of text data, the research in NLP needs more sophisticated methods than traditional statistical methods. Current day approaches make use …

Predicting Early Indicators Of Cognitive Decline From Verbal Utterances, Swati Padhee, Anurag Illendula, Megan Sadler, Valerie L. Shalin, Tanvi Banerjee, Krishnaprasad Thirunarayan, William Romine

Computer Science and Engineering Faculty Publications

Dementia is a group of irreversible, chronic, and progressive neurodegenerative disorders resulting in impaired memory, communication, and thought processes. In recent years, clinical research advances in brain aging have focused on the earliest clinically detectable stage of incipient dementia, commonly known as mild cognitive impairment (MCI). Currently, these disorders are diagnosed using a manual analysis of neuropsychological examinations. We measure the feasibility of using the linguistic characteristics of verbal utterances elicited during neuropsychological exams of elderly subjects to distinguish between elderly control groups, people with MCI, people diagnosed with possible Alzheimer's disease (AD), and probable AD. We investigated the performance …

Separating Content Selection From Surface Realization In Neural Text Summarization, Logan Lebanoff

Electronic Theses and Dissertations, 2020-2023

Text summarization is a rapidly growing field with many new innovations. End-to-end models using the sequence-to-sequence architecture achieve high scores according to automatic metrics on standard datasets. However, they frequently generate summaries that are factually inconsistent with the original article -- a vital problem to be solved before the summaries can be used in real-world applications. In addition, they are not generalizable to new domains, especially those with few training examples. In this dissertation, we propose to explicitly separate the two steps of content selection and surface realization in summarization. Content selection is the process of choosing important words/phrases/sentences from …

A User-Centric And Sentiment Aware Privacy-Disclosure Detection Framework Based On Multi-Input Neural Network, A. K. M. Nuhil Mehdy, Hoda Mehrpouyan

Computer Science Faculty Publications and Presentations

Data and information privacy is a major concern of today’s world. More specifically, users’ digital privacy has become one of the most important issues to deal with, as advancements are being made in information sharing technology. An increasing number of users are sharing information through text messages, emails, and social media without proper awareness of privacy threats and their consequences. One approach to prevent the disclosure of private information is to identify them in a conversation and warn the dispatcher before the conveyance happens between the sender and the receiver. Another way of preventing information (sensitive) loss might be to …

Detecting Fake News Spreaders In Social Networks Via Linguistic And Personality Features: Notebook For Pan At Clef 2020, Anu Shrestha, Francesca Spezzano, Abishai Joy

Computer Science Faculty Publications and Presentations

This paper addresses the problem of automatically detecting fake news spreaders in social networks such as Twitter. We model the problem as a binary classification task and consider several groups of features, including writing style, word and char n-grams, BERT semantic embedding, and sentiment analysis, which are computed from a set of tweets each user authored. Our proposed approach is evaluated on the dataset made available by the PAN at CLEF 2020 shared task on profiling fake news spreader, which provided labeled data in both English and Spanish. Experimental results show that we can detect fake news spreaders with an …

You Don’T Say... Linguistic Features In Sarcasm Detection, Martina Ducret, Lauren Kruse, Carlos Martinez, Anna Feldman, Jing Peng

Department of Computer Science Faculty Scholarship and Creative Works

We explore linguistic features that contribute to sarcasm detection. The linguistic features that we investigate are a combination of text and word complexity, stylistic and psychological features. We experiment with sarcastic tweets with and without context. The results of our experiments indicate that contextual information is crucial for sarcasm prediction. One important observation is that sarcastic tweets are typically incongruent with their context in terms of sentiment or emotional load.

A Survey On Recognizing Textual Entailment As An Nlp Evaluation, Adam Poliak

Computer Science Faculty Research and Scholarship

Recognizing Textual Entailment (RTE) was proposed as a unified evaluation framework to compare semantic understanding of different NLP systems. In this survey paper, we provide an overview of different approaches for evaluating and understanding the reasoning capabilities of NLP systems. We then focus our discussion on RTE by highlighting prominent RTE datasets as well as advances in RTE dataset that focus on specific linguistic phenomena that can be used to evaluate NLP systems on a fine-grained level. We conclude by arguing that when evaluating NLP systems, the community should utilize newly introduced RTE datasets that focus on specific linguistic phenomena.

You Might Be A Robot, Bryan Casey, Mark A. Lemley

Cornell Law Review

As robots and artificial intelligence (Al) increase their influence over society, policymakers are increasingly regulating them. But to regulate these technologies, we first need to know what they are. And here we come to a problem. No one has been able to offer a decent definition of robots arid AI-not even experts. What's more, technological advances make it harder and harder each day to tell people from robots and robots from "dumb" machines. We have already seen disastrous legal definitions written with one target in mind inadvertently affecting others. In fact, if you are reading this you are (probably) not …

Exploring The Power Of Supervised Learning Methods For Company Name Disambiguation In Microblog Posts, Nafi̇ye Polat, Ali̇ Çakmak, Rabi̇a Turan

Turkish Journal of Electrical Engineering and Computer Sciences

Twitter is an online social networking website where people can post short messages on any subject, and these messages become visible to other users. Users intentionally express their opinions about companies or products via microblogging texts. Analyzing such messages might help explore what customers think about company products, or what the broad feelings of customers are. Identifying tweets referring to products and companies is becoming an important tool recently. However, company names are often vague. Hence, the first step is to locate the messages that are relevant to a company. In this paper, we present a number of supervised learning …