Human language processing is incremental. In this dissertation, I explore how an incremental perspective can help us clarify our understanding of transformational syntax, which typically proceeds bottom-up. As part of our exploration, I develop an incremental head-driven parsing algorithm for Minimalist Grammars. The two main innovations of this parsing algorithm...
Machine learning is seeping into every fabric in various practical domains such as autonomous driving, wearable computing, and smart buildings. However, in the actual development and integration, especially when the learning-based components are frequently included as components of large complex systems where the physical instances can be included as interactable...
At its core, the purpose of microscopy is to make objects and their underlying structures visible under high magnification. With the remarkable progress of electron microscopy, the sub-micron “high” magnification of light microscopy has been completely refashioned to encompass subatomic length scales. Unfortunately, higher-magnification does little to negate existing interpretability...
Mission-critical systems are those imperative systems whose failures can result in catastrophic consequences. Traditional techniques, such as manual investigation and testing, cannot ensure the absence of errors and security vulnerabilities within these systems. This dissertation leverages formal methods to comprehensively examine several mission-critical systems and their essential components. For each...
Task-oriented conversational systems are becoming increasingly popular, as shown by the rise of conversational recommendation systems across multiple platforms (e.g., Google Home, Alexa, and Siri) and domains (e.g., local establishments, e-commerce, books, music, and movies). However, users are still largely limited in what preferences they can express and how, as...
Task-oriented conversational systems are becoming increasingly popular, as shown by the rise of conversational recommendation systems across multiple platforms (e.g., Google Home, Alexa, and Siri) and domains (e.g., local establishments, e-commerce, books, music, and movies). However, users are still largely limited in what preferences they can express and how, as...
Modern data sets are increasingly vast, not only in the number of samples, but also in the number of measurements, or features, that they contain. This high-dimensionality poses a unique set of problems for data analysis due to a set of phenomena known as ``the curse of dimensionality.'' This thesis...
Recovering three-dimensional (3D) structural information of a specimen from a single two-dimensional (2D) measurement remains an important but challenging task in microscopic imaging. A conventional 2D microscopic image has a shallow depth-of-focus (DoF). Thus, recovering 3D information usually requires sequentially z-scanning the focal planes. This process is time consuming and...
Automated sketch collaborators might help us create more dynamic intelligent tutoring systems, work out designs, reduce bias in solving spatial social problems, and organize our ideas. Here, we examine some properties of sketch recognition methods designed to help serve that goal. Structure Mapping techniques are applied to symbolic structural descriptions...
Natural Language Processing methods have become increasingly important for a variety of high- and low-level tasks including speech recognition, question answering, and automatic language translation. The state of the art performance of these methods is continuously advancing, but reliance on labeled training data sets often creates an artificial upper bound...
A massive amount of data is generated every second all around the world. Machine learning becomes the most attractive solution to consume the data fuel and transform it into productivity. It has yielded great results in many fields, such as healthcare, marketing, finance, etc. Machine learning models are usually designed...
Over the past decade as smartphones and wearable tracking devices have grown in popularity, more individuals have begun collecting their own health and behavioral data. Innovations in sensor technology now allow individuals to continuously collect data over long periods of time with minimal effort. As a result, more data has...
Art has been tied to scientific and technological advancements throughout history, providing methods and mediums for communication, expression, and exploration. Art is a dialogic domain that evolves with the technological advances in society–incorporating technology and computational tools to create new genres of art. We live in an increasingly computational and...
When first-year students begin college they are thrown into a new environment where they are expected to simultaneously perform academically, form new relationships, and become independent. Many students struggle with this transition; experiences of stress, anxiety, and depression are common. For the majority of residential college students this is their...
This dissertation explores the design and evaluation of augmentative and alternative communication (AAC) technologies for people with aphasia. Humans use speech and language to communicate their thoughts and opinions as well as express their individuality, autonomy and agency (George Armitage Miller 1951; Ahearn 2001). Speech and language are important tools...
In response to exponentially increasing demand for digital media, today's Internet landscape has evolved into a multitude of diverse and interdependent distribution systems designed to move content as efficiently as possible. While many of these systems have \emph{individually} been explored in depth by both academic and industrial communities, a cross-sectional...
Citizen media literacy is essential in a democratic society, particularly in the online environment where valid media sources have proliferated alongside purveyors of fake news. This dissertation explores technologies that automatically detect aspects of bias in news articles, with the ultimate aim of leveraging them to augment media literacy. It...
Millions of people freelance in the growing online gig economy, making it important to advance pay equity and support freelancers in earning their livelihoods online. Compared to offline employment, freelancing introduces at least two challenges that threaten freelancers’ ability to secure work and the equitability of the gig economy: 1)...
Historically, there have been large disparities in the degree to which different communities have access to resources and representation within society. With the increased availability of the internet and the growth of user-generated content platforms like Twitter and Wikipedia, there are opportunities to alleviate some these long-standing barriers to access...
Wearable visual systems, such as ego-centric wearable cameras, have failed to integrate into everyday life. We have witnessed the abandonment of wearable visual systems as consumer devices (e.g., Google Glass) and as research tools (e.g., SenseCam). While it is natural for some technologies to die out, visual wearable systems are...
The production and spread of digital news involves a wide range of actors: journalists and the organizations that employ them, social media platforms, audiences, and myriad commentators, citizen journalists, bloggers, and other actors who contribute to the news ecosystem without inhabiting an official role. These actors interact in flexible, often...
Supervised learning model is one of the most fundamental machine learning models. It can provide powerful capability of prediction by learning complex patterns hidden in many, sometimes thousands, predictors. It can also be used as a building block of other machine learning tasks, like unsupervised learning and reinforcement learning. Such...
The analytical paradigm in philosophy has as a pillar an analysis of the sentence as a basic entity. New sentences may be built from old sentences recursively through the application of logical constants, recently including intensional operators. Models are built on how these logical constants interact with each other, and...
In this dissertation, we aim to develop algorithms that achieve optimality with provable complexity guarantees under various settings in reinforcement learning (RL). Specifically, in Markov decision processes (MDPs), we study single-agent and multi-agent online RL, respectively, and offline RL under the presence of unobserved confounders. Single-agent online RL. We design...
Deep neural networks have shown impressive performance for many applications. In this dissertation, leveraging the capabilities of neural networks for modeling the non-linearity exists in the data, we propose several models that can project data into a low dimensional, discriminative, and smooth manifold. The suggested models can transfer knowledge from...
Since the invitation of ARPANet in 1969, network protocols and communication systems have continued to emerge. Especially in the past decade, the prosperity of mobile internet and cloud computing has resulted in a large number of network protocols and communication systems, which have become critical infrastructure for our society. Availability...
Security and robustness are two critical problems in modern computing system. In this disserta- tion, we study these two problems in both hardware system and learning system.Firstly, we discuss the robustness problem in hardware system. Modern microprocessors suffer from significant on-chip variation at the advanced technology nodes. The development of...
Public-facing data-driven technologies such as social media platforms and search engines rely on data producers, such as users and crowd workers, to be feasible and financially sustainable. Recently, it became clear that the goals of these data-driven technologies do not always align with those of the public, causing public backlashes...
The rise and racial gap in maternal mortality and morbidity in the US growing public health crisis. The US maternal mortality rate is double that of peer countries such as the UK and Canada. Even more striking, Black women are 243% more likely to die from childbirth-related causes. According to...
The language Esterel has found success in many safety-critical applications, from aircraft landing gear to digital signal processors. Its unique combination of powerful control operations, deterministic concurrency, and real time execution bounds are indispensable to programmer in these kinds of safety-critical domains. However these features lead to an interesting facet...
Human communication has become increasingly reliant on systems made and managed by large technology companies like Google, Apple, Twitter, and Meta (formerly Facebook). These systems offer people many benefits, but they also present new challenges for society. In recent years, researchers, lawmakers, and journalists have suggested that large technology companies...
This research looks at the robotic shape formation problem, which is one of the fundamental problems in robotic swarm systems. Here, the task is to move a group of robots to form a user-specified shape. In this dissertation, the task of shape formation is divided to four problems: (i) using...
In recent years, machine learning on graphs (or networks) has gone from a niche topic with only a few active researchers worldwide, to a heavily invested field with novel use cases for dealing with relationships and/or interactions within complex systems in the natural and social sciences. Traditionally, choosing the right...
Existing nonlinear optimization methods have proven reliable over the past few decades for a wide range of applications but have critically relied on accurate function and gradient evaluations. Modern nonlinear optimization problems arising from machine learning and scientific computing applications are increasingly complex and large scale, which make accurate evaluations...
The world is awash in data and much of artificial intelligence focuses on learning models of the underlying structure in this data or the mechanisms governing its evolution. Both neural and symbolic models have weaknesses that make these models sub-optimal from a use perspective. Much of this data is in...
X-ray imaging at nano and micro-scale is of great importance for the material science and defense industry. Large penetration depth and low wavelength of x-rays offer an important potential to image objects at high resolution and in a non-invasive process. While the ever-growing community is pursuing novel applications and looking...
This dissertation introduces several novel computational imaging techniques that capture and analyze the 3D surface shapes and internal layered materials. The research proposes user-friendly and non-invasive imaging systems, constructed using only commercial off-the-shelf (COTS) components, which provide accurate measurement of 3D information that was previously inaccessible. The dissertation focuses on...
Language models are the foundation of many natural language tasks such as machine translation, speech recognition, and dialogue systems. Modeling the probability distributions of text accurately helps capture the structures of language and extract valuable information contained in various corpora. In recent years, many advanced models have achieved state-of-the-art performance...
Many volunteer communities rely on technological systems to help their members connect, collaborate and learn the norms of how to participate in the organization. This dissertation presents research that examines technological interventions designed to support participation in three different volunteer-run communities, all of which have porous boundaries, and allow volunteers...
Visual Question Answering (VQA) increasingly attracts industry and academia attention. It requires the model to provide a natural language answer by an image and a related natural language question. Meanwhile, it relates to multidisciplinary research such as natural language understanding, visual information retrieval, and multimodal reasoning. As a multimodality task,...
Our experience of the physical world is mediated by our senses, but while most people have five senses, interactions with computer systems are largely limited to the visual sense. When working with nonvisual artifacts, like sound, on computers, such artifacts are typically transformed, or re-encoded, into something visual. Determining how...
Three-dimensional (3D) imaging has been widely used in academic research and industrial applications. Compared to 2D representations, 3D imaging can yield more information about geometric structures of an object such as small surface variations that are difficult to perceive otherwise. 3D image contents provide additional information that is complementary to...
We live in an increasingly computational world; one that, in the near term, may require everyone to be computationally literate. Computer science (CS) education has greatly increased its reach in the last two decades with an increasing number of students having access to formal computer science classroom experiences in the...
The study and design of machines that are able to analyze the auditory scene and organize sound into parts that are perceptually meaningful to humans is referred to as machine hearing. Such machines are expected to distinguish between different sound categories (e.g., speech, music, background noise), focus on a sound...
Imagine sitting in a room listening to some friends play a song. Perhaps one friend is playing guitar, another playing bass, and a third is playing drums. The musical content in this scene is extraordinarily complex, yet it contains many types of structure that is easy for us to comprehend....
In the late 2000’s, scientific studies in cultural heritage saw a great advancement in macro X-ray fluorescence (XRF) imaging of paintings. These images are used to generate elemental distribution maps, which aid in identifying chemical elements and paint pig- ments as well as their locations throughout the layers of the...
Location-aware technologies, such as personal navigation applications, location-based AR games, and artificial intelligence systems that learn from data about places, increasingly mediate our understanding of and interactions with the world. However, a number of risks associated with location-aware technologies have emerged, jeopardizing the welfare of its users. This dissertation seeks...
Due to their widespread applicability, graphs and networks appear in various contexts. The increasing scale of graphs encountered in the real-world requires the developmentof efficient algorithms that run reasonably fast and produce close to optimal solutions.
The main focus of this thesis is the development of fast graph algorithms for...
Social media and online forums provide spaces where people can gather beyond restrictions of geographic proximity. For some individuals with mental illness, these spaces are vital; providing outlets and communities where a multitude of experiences are accepted and understood, rather than judged against normative, often ableist standards. For nearly three...
Surface appearance represents the sense impression of the surface. In visual art, the artists try to use the appearance of their artworks to express their mental state and philosophy. Researchers in the cultural heritage community has been trying to use different analysis approaches to interpret artworks. In Computer Graphics and...