Matching Items (68)
Filtering by
- All Subjects: Computer Science
- All Subjects: Evaluation
- Creators: Baral, Chitta
- Status: Published
Description
Nearly 25 years ago, parallel computing techniques were first applied to vector spatial analysis methods. This initial research was driven by the desire to reduce computing times in order to support scaling to larger problem sets. Since this initial work, rapid technological advancement has driven the availability of High Performance Computing (HPC) resources, in the form of multi-core desktop computers, distributed geographic information processing systems, e.g. computational grids, and single site HPC clusters. In step with increases in computational resources, significant advancement in the capabilities to capture and store large quantities of spatially enabled data have been realized. A key component to utilizing vast data quantities in HPC environments, scalable algorithms, have failed to keep pace. The National Science Foundation has identified the lack of scalable algorithms in codified frameworks as an essential research product. Fulfillment of this goal is challenging given the lack of a codified theoretical framework mapping atomic numeric operations from the spatial analysis stack to parallel programming paradigms, the diversity in vernacular utilized by research groups, the propensity for implementations to tightly couple to under- lying hardware, and the general difficulty in realizing scalable parallel algorithms. This dissertation develops a taxonomy of parallel vector spatial analysis algorithms with classification being defined by root mathematical operation and communication pattern, a computational dwarf. Six computational dwarfs are identified, three being drawn directly from an existing parallel computing taxonomy and three being created to capture characteristics unique to spatial analysis algorithms. The taxonomy provides a high-level classification decoupled from low-level implementation details such as hardware, communication protocols, implementation language, decomposition method, or file input and output. By taking a high-level approach implementation specifics are broadly proposed, breadth of coverage is achieved, and extensibility is ensured. The taxonomy is both informed and informed by five case studies im- plemented across multiple, divergent hardware environments. A major contribution of this dissertation is a theoretical framework to support the future development of concrete parallel vector spatial analysis frameworks through the identification of computational dwarfs and, by extension, successful implementation strategies.
ContributorsLaura, Jason (Author) / Rey, Sergio J. (Thesis advisor) / Anselin, Luc (Committee member) / Wang, Shaowen (Committee member) / Li, Wenwen (Committee member) / Arizona State University (Publisher)
Created2015
Description
For the past three decades, the design of an effective strategy for generating poetry that matches that of a human’s creative capabilities and complexities has been an elusive goal in artificial intelligence (AI) and natural language generation (NLG) research, and among linguistic creativity researchers in particular. This thesis presents a novel approach to fixed verse poetry generation using neural word embeddings. During the course of generation, a two layered poetry classifier is developed. The first layer uses a lexicon based method to classify poems into types based on form and structure, and the second layer uses a supervised classification method to classify poems into subtypes based on content with an accuracy of 92%. The system then uses a two-layer neural network to generate poetry based on word similarities and word movements in a 50-dimensional vector space.
The verses generated by the system are evaluated using rhyme, rhythm, syllable counts and stress patterns. These computational features of language are considered for generating haikus, limericks and iambic pentameter verses. The generated poems are evaluated using a Turing test on both experts and non-experts. The user study finds that only 38% computer generated poems were correctly identified by nonexperts while 65% of the computer generated poems were correctly identified by experts. Although the system does not pass the Turing test, the results from the Turing test suggest an improvement of over 17% when compared to previous methods which use Turing tests to evaluate poetry generators.
The verses generated by the system are evaluated using rhyme, rhythm, syllable counts and stress patterns. These computational features of language are considered for generating haikus, limericks and iambic pentameter verses. The generated poems are evaluated using a Turing test on both experts and non-experts. The user study finds that only 38% computer generated poems were correctly identified by nonexperts while 65% of the computer generated poems were correctly identified by experts. Although the system does not pass the Turing test, the results from the Turing test suggest an improvement of over 17% when compared to previous methods which use Turing tests to evaluate poetry generators.
ContributorsMagge, Arjun (Author) / Syrotiuk, Violet R. (Thesis advisor) / Baral, Chitta (Committee member) / Hogue, Cynthia (Committee member) / Bazzi, Rida (Committee member) / Arizona State University (Publisher)
Created2016
Description
Question Answering has been under active research for decades, but it has recently taken the spotlight following IBM Watson's success in Jeopardy! and digital assistants such as Apple's Siri, Google Now, and Microsoft Cortana through every smart-phone and browser. However, most of the research in Question Answering aims at factual questions rather than deep ones such as ``How'' and ``Why'' questions.
In this dissertation, I suggest a different approach in tackling this problem. We believe that the answers of deep questions need to be formally defined before found.
Because these answers must be defined based on something, it is better to be more structural in natural language text; I define Knowledge Description Graphs (KDGs), a graphical structure containing information about events, entities, and classes. We then propose formulations and algorithms to construct KDGs from a frame-based knowledge base, define the answers of various ``How'' and ``Why'' questions with respect to KDGs, and suggest how to obtain the answers from KDGs using Answer Set Programming. Moreover, I discuss how to derive missing information in constructing KDGs when the knowledge base is under-specified and how to answer many factual question types with respect to the knowledge base.
After having the answers of various questions with respect to a knowledge base, I extend our research to use natural language text in specifying deep questions and knowledge base, generate natural language text from those specification. Toward these goals, I developed NL2KR, a system which helps in translating natural language to formal language. I show NL2KR's use in translating ``How'' and ``Why'' questions, and generating simple natural language sentences from natural language KDG specification. Finally, I discuss applications of the components I developed in Natural Language Understanding.
In this dissertation, I suggest a different approach in tackling this problem. We believe that the answers of deep questions need to be formally defined before found.
Because these answers must be defined based on something, it is better to be more structural in natural language text; I define Knowledge Description Graphs (KDGs), a graphical structure containing information about events, entities, and classes. We then propose formulations and algorithms to construct KDGs from a frame-based knowledge base, define the answers of various ``How'' and ``Why'' questions with respect to KDGs, and suggest how to obtain the answers from KDGs using Answer Set Programming. Moreover, I discuss how to derive missing information in constructing KDGs when the knowledge base is under-specified and how to answer many factual question types with respect to the knowledge base.
After having the answers of various questions with respect to a knowledge base, I extend our research to use natural language text in specifying deep questions and knowledge base, generate natural language text from those specification. Toward these goals, I developed NL2KR, a system which helps in translating natural language to formal language. I show NL2KR's use in translating ``How'' and ``Why'' questions, and generating simple natural language sentences from natural language KDG specification. Finally, I discuss applications of the components I developed in Natural Language Understanding.
ContributorsVo, Nguyen Ha (Author) / Baral, Chitta (Thesis advisor) / Lee, Joohyung (Committee member) / VanLehn, Kurt (Committee member) / Tran, Son Cao (Committee member) / Arizona State University (Publisher)
Created2015
Description
Science instructors need questions for use in exams, homework assignments, class discussions, reviews, and other instructional activities. Textbooks never have enough questions, so instructors must find them from other sources or generate their own questions. In order to supply instructors with biology questions, a semantic network approach was developed for generating open response biology questions. The generated questions were compared to professional authorized questions.
To boost students’ learning experience, adaptive selection was built on the generated questions. Bayesian Knowledge Tracing was used as embedded assessment of the student’s current competence so that a suitable question could be selected based on the student’s previous performance. A between-subjects experiment with 42 participants was performed, where half of the participants studied with adaptive selected questions and the rest studied with mal-adaptive order of questions. Both groups significantly improved their test scores, and the participants in adaptive group registered larger learning gains than participants in the control group.
To explore the possibility of generating rich instructional feedback for machine-generated questions, a question-paragraph mapping task was identified. Given a set of questions and a list of paragraphs for a textbook, the goal of the task was to map the related paragraphs to each question. An algorithm was developed whose performance was comparable to human annotators.
A multiple-choice question with high quality distractors (incorrect answers) can be pedagogically valuable as well as being much easier to grade than open-response questions. Thus, an algorithm was developed to generate good distractors for multiple-choice questions. The machine-generated multiple-choice questions were compared to human-generated questions in terms of three measures: question difficulty, question discrimination and distractor usefulness. By recruiting 200 participants from Amazon Mechanical Turk, it turned out that the two types of questions performed very closely on all the three measures.
To boost students’ learning experience, adaptive selection was built on the generated questions. Bayesian Knowledge Tracing was used as embedded assessment of the student’s current competence so that a suitable question could be selected based on the student’s previous performance. A between-subjects experiment with 42 participants was performed, where half of the participants studied with adaptive selected questions and the rest studied with mal-adaptive order of questions. Both groups significantly improved their test scores, and the participants in adaptive group registered larger learning gains than participants in the control group.
To explore the possibility of generating rich instructional feedback for machine-generated questions, a question-paragraph mapping task was identified. Given a set of questions and a list of paragraphs for a textbook, the goal of the task was to map the related paragraphs to each question. An algorithm was developed whose performance was comparable to human annotators.
A multiple-choice question with high quality distractors (incorrect answers) can be pedagogically valuable as well as being much easier to grade than open-response questions. Thus, an algorithm was developed to generate good distractors for multiple-choice questions. The machine-generated multiple-choice questions were compared to human-generated questions in terms of three measures: question difficulty, question discrimination and distractor usefulness. By recruiting 200 participants from Amazon Mechanical Turk, it turned out that the two types of questions performed very closely on all the three measures.
ContributorsZhang, Lishang (Author) / VanLehn, Kurt (Thesis advisor) / Baral, Chitta (Committee member) / Hsiao, Ihan (Committee member) / Wright, Christian (Committee member) / Arizona State University (Publisher)
Created2015
Description
Current work in planning assumes that user preferences and/or domain dynamics are completely specified in advance, and aims to search for a single solution plan to satisfy these. In many real world scenarios, however, providing a complete specification of user preferences and domain dynamics becomes a time-consuming and error-prone task. More often than not, a user may provide no knowledge or at best partial knowledge of her preferences with respect to a desired plan. Similarly, a domain writer may only be able to determine certain parts, not all, of the model of some actions in a domain. Such modeling issues requires new concepts on what a solution should be, and novel techniques in solving the problem. When user preferences are incomplete, rather than presenting a single plan, the planner must instead provide a set of plans containing one or more plans that are similar to the one that the user prefers. This research first proposes the usage of different measures to capture the quality of such plan sets. These are domain-independent distance measures based on plan elements if no knowledge of the user preferences is given, or the Integrated Preference Function measure in case incomplete knowledge of such preferences is provided. It then investigates various heuristic approaches to generate plan sets in accordance with these measures, and presents empirical results demonstrating the promise of the methods. The second part of this research addresses planning problems with incomplete domain models, specifically those annotated with possible preconditions and effects of actions. It formalizes the notion of plan robustness capturing the probability of success for plans during execution. A method of assessing plan robustness based on the weighted model counting approach is proposed. Two approaches for synthesizing robust plans are introduced. The first one compiles the robust plan synthesis problems to the conformant probabilistic planning problems. The second approximates the robustness measure with lower and upper bounds, incorporating them into a stochastic local search for estimating distance heuristic to a goal state. The resulting planner outperforms a state-of-the-art planner that can handle incomplete domain models in both plan quality and planning time.
ContributorsNguyễn, Tuấn Anh (Author) / Kambhampati, Subbarao (Thesis advisor) / Baral, Chitta (Committee member) / Do, Minh (Committee member) / Lee, Joohyung (Committee member) / Smith, David E. (Committee member) / Arizona State University (Publisher)
Created2014
Description
Modeling dynamic systems is an interesting problem in Knowledge Representation (KR) due to their usefulness in reasoning about real-world environments. In order to effectively do this, a number of different formalisms have been considered ranging from low-level languages, such as Answer Set Programming (ASP), to high-level action languages, such as C+ and BC. These languages show a lot of promise over many traditional approaches as they allow a developer to automate many tasks which require reasoning within dynamic environments in a succinct and elaboration tolerant manner. However, despite their strengths, they are still insufficient for modeling many systems, especially those of non-trivial scale or that require the ability to cope with exceptions which occur during execution, such as unexpected events or unintended consequences to actions which have been performed. In order to address these challenges, a theoretical framework is created which focuses on improving the feasibility of applying KR techniques to such problems. The framework is centered on the action language BC+, which integrates many of the strengths of existing KR formalisms, and provides the ability to perform efficient reasoning in an incremental fashion while handling exceptions which occur during execution. The result is a developer friendly formalism suitable for performing reasoning in an online environment. Finally, the newly enhanced Cplus2ASP 2 is introduced, which provides a number of improvements over the original version. These improvements include implementing BC+ among several additional languages, providing enhanced developer support, and exhibiting a significant performance increase over its predecessors and similar systems.
ContributorsBabb, Joseph (Author) / Lee, Joohyung (Thesis advisor) / Lee, Yann-Hang (Committee member) / Baral, Chitta (Committee member) / Arizona State University (Publisher)
Created2014
Description
There have been extensive research in how news and twitter feeds can affect the outcome of a given stock. However, a majority of this research has studied the short term effects of sentiment with a given stock price. Within this research, I studied the long-term effects of a given stock price using fundamental analysis techniques. Within this research, I collected both sentiment data and fundamental data for Apple Inc., Microsoft Corp., and Peabody Energy Corp. Using a neural network algorithm, I found that sentiment does have an effect on the annual growth of these companies but the fundamentals are more relevant when determining overall growth. The stocks which show more consistent growth hold more importance on the previous year’s stock price but companies which have less consistency in their growth showed more reliance on the revenue growth and sentiment on the overall company and CEO. I discuss how I collected my research data and used a multi-layered perceptron to predict a threshold growth of a given stock. The threshold used for this particular research was 10%. I then showed the prediction of this threshold using my perceptron and afterwards, perform an f anova test on my choice of features. The results showed the fundamentals being the better predictor of stock information but fundamentals came in a close second in several cases, proving sentiment does hold an effect over long term growth.
ContributorsReeves, Tyler Joseph (Author) / Davulcu, Hasan (Thesis advisor) / Baral, Chitta (Committee member) / Cesta, John (Committee member) / Arizona State University (Publisher)
Created2016
Description
Due to vast resources brought by social media services, social data mining has
received increasing attention in recent years. The availability of sheer amounts of
user-generated data presents data scientists both opportunities and challenges. Opportunities are presented with additional data sources. The abundant link information
in social networks could provide another rich source in deriving implicit information
for social data mining. However, the vast majority of existing studies overwhelmingly
focus on positive links between users while negative links are also prevailing in real-
world social networks such as distrust relations in Epinions and foe links in Slashdot.
Though recent studies show that negative links have some added value over positive
links, it is dicult to directly employ them because of its distinct characteristics from
positive interactions. Another challenge is that label information is rather limited
in social media as the labeling process requires human attention and may be very
expensive. Hence, alternative criteria are needed to guide the learning process for
many tasks such as feature selection and sentiment analysis.
To address above-mentioned issues, I study two novel problems for signed social
networks mining, (1) unsupervised feature selection in signed social networks; and
(2) unsupervised sentiment analysis with signed social networks. To tackle the first problem, I propose a novel unsupervised feature selection framework SignedFS. In
particular, I model positive and negative links simultaneously for user preference
learning, and then embed the user preference learning into feature selection. To study the second problem, I incorporate explicit sentiment signals in textual terms and
implicit sentiment signals from signed social networks into a coherent model Signed-
Senti. Empirical experiments on real-world datasets corroborate the effectiveness of
these two frameworks on the tasks of feature selection and sentiment analysis.
received increasing attention in recent years. The availability of sheer amounts of
user-generated data presents data scientists both opportunities and challenges. Opportunities are presented with additional data sources. The abundant link information
in social networks could provide another rich source in deriving implicit information
for social data mining. However, the vast majority of existing studies overwhelmingly
focus on positive links between users while negative links are also prevailing in real-
world social networks such as distrust relations in Epinions and foe links in Slashdot.
Though recent studies show that negative links have some added value over positive
links, it is dicult to directly employ them because of its distinct characteristics from
positive interactions. Another challenge is that label information is rather limited
in social media as the labeling process requires human attention and may be very
expensive. Hence, alternative criteria are needed to guide the learning process for
many tasks such as feature selection and sentiment analysis.
To address above-mentioned issues, I study two novel problems for signed social
networks mining, (1) unsupervised feature selection in signed social networks; and
(2) unsupervised sentiment analysis with signed social networks. To tackle the first problem, I propose a novel unsupervised feature selection framework SignedFS. In
particular, I model positive and negative links simultaneously for user preference
learning, and then embed the user preference learning into feature selection. To study the second problem, I incorporate explicit sentiment signals in textual terms and
implicit sentiment signals from signed social networks into a coherent model Signed-
Senti. Empirical experiments on real-world datasets corroborate the effectiveness of
these two frameworks on the tasks of feature selection and sentiment analysis.
ContributorsCheng, Kewei (Author) / Liu, Huan (Thesis advisor) / Tong, Hanghang (Committee member) / Baral, Chitta (Committee member) / Arizona State University (Publisher)
Created2017
Description
A major challenge in health-related policy and program evaluation research is attributing underlying causal relationships where complicated processes may exist in natural or quasi-experimental settings. Spatial interaction and heterogeneity between units at individual or group levels can violate both components of the Stable-Unit-Treatment-Value-Assumption (SUTVA) that are core to the counterfactual framework, making treatment effects difficult to assess. New approaches are needed in health studies to develop spatially dynamic causal modeling methods to both derive insights from data that are sensitive to spatial differences and dependencies, and also be able to rely on a more robust, dynamic technical infrastructure needed for decision-making. To address this gap with a focus on causal applications theoretically, methodologically and technologically, I (1) develop a theoretical spatial framework (within single-level panel econometric methodology) that extends existing theories and methods of causal inference, which tend to ignore spatial dynamics; (2) demonstrate how this spatial framework can be applied in empirical research; and (3) implement a new spatial infrastructure framework that integrates and manages the required data for health systems evaluation.
The new spatially explicit counterfactual framework considers how spatial effects impact treatment choice, treatment variation, and treatment effects. To illustrate this new methodological framework, I first replicate a classic quasi-experimental study that evaluates the effect of drinking age policy on mortality in the United States from 1970 to 1984, and further extend it with a spatial perspective. In another example, I evaluate food access dynamics in Chicago from 2007 to 2014 by implementing advanced spatial analytics that better account for the complex patterns of food access, and quasi-experimental research design to distill the impact of the Great Recession on the foodscape. Inference interpretation is sensitive to both research design framing and underlying processes that drive geographically distributed relationships. Finally, I advance a new Spatial Data Science Infrastructure to integrate and manage data in dynamic, open environments for public health systems research and decision- making. I demonstrate an infrastructure prototype in a final case study, developed in collaboration with health department officials and community organizations.
The new spatially explicit counterfactual framework considers how spatial effects impact treatment choice, treatment variation, and treatment effects. To illustrate this new methodological framework, I first replicate a classic quasi-experimental study that evaluates the effect of drinking age policy on mortality in the United States from 1970 to 1984, and further extend it with a spatial perspective. In another example, I evaluate food access dynamics in Chicago from 2007 to 2014 by implementing advanced spatial analytics that better account for the complex patterns of food access, and quasi-experimental research design to distill the impact of the Great Recession on the foodscape. Inference interpretation is sensitive to both research design framing and underlying processes that drive geographically distributed relationships. Finally, I advance a new Spatial Data Science Infrastructure to integrate and manage data in dynamic, open environments for public health systems research and decision- making. I demonstrate an infrastructure prototype in a final case study, developed in collaboration with health department officials and community organizations.
ContributorsKolak, Marynia Aniela (Author) / Anselin, Luc (Thesis advisor) / Rey, Sergio (Committee member) / Koschinsky, Julia (Committee member) / Maciejewski, Ross (Committee member) / Arizona State University (Publisher)
Created2017
Description
In this thesis, I propose a new technique of Aligning English sentence words
with its Semantic Representation using Inductive Logic Programming(ILP). My
work focusses on Abstract Meaning Representation(AMR). AMR is a semantic
formalism to English natural language. It encodes meaning of a sentence in a rooted
graph. This representation has gained attention for its simplicity and expressive power.
An AMR Aligner aligns words in a sentence to nodes(concepts) in its AMR
graph. As AMR annotation has no explicit alignment with words in English sentence,
automatic alignment becomes a requirement for training AMR parsers. The aligner in
this work comprises of two components. First, rules are learnt using ILP that invoke
AMR concepts from sentence-AMR graph pairs in the training data. Second, the
learnt rules are then used to align English sentences with AMR graphs. The technique
is evaluated on publicly available test dataset and the results are comparable with
state-of-the-art aligner.
with its Semantic Representation using Inductive Logic Programming(ILP). My
work focusses on Abstract Meaning Representation(AMR). AMR is a semantic
formalism to English natural language. It encodes meaning of a sentence in a rooted
graph. This representation has gained attention for its simplicity and expressive power.
An AMR Aligner aligns words in a sentence to nodes(concepts) in its AMR
graph. As AMR annotation has no explicit alignment with words in English sentence,
automatic alignment becomes a requirement for training AMR parsers. The aligner in
this work comprises of two components. First, rules are learnt using ILP that invoke
AMR concepts from sentence-AMR graph pairs in the training data. Second, the
learnt rules are then used to align English sentences with AMR graphs. The technique
is evaluated on publicly available test dataset and the results are comparable with
state-of-the-art aligner.
ContributorsAgarwal, Shubham (Author) / Baral, Chitta (Thesis advisor) / Li, Baoxin (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2017