Matching Items (90)
Filtering by
- All Subjects: Computer Science
- Creators: Baral, Chitta
- Member of: Theses and Dissertations
- Member of: ASU Electronic Theses and Dissertations
Description
The objective of this research is to determine an approach for automating the learning of the initial lexicon used in translating natural language sentences to their formal knowledge representations based on lambda-calculus expressions. Using a universal knowledge representation and its associated parser, this research attempts to use word alignment techniques to align natural language sentences to the linearized parses of their associated knowledge representations in order to learn the meanings of individual words. The work includes proposing and analyzing an approach that can be used to learn some of the initial lexicon.
ContributorsBaldwin, Amy Lynn (Author) / Baral, Chitta (Thesis director) / Vo, Nguyen (Committee member) / Industrial, Systems (Contributor) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2015-05
Description
Education of any skill based subject, such as mathematics or language, involves a significant amount of repetition and pratice. According to the National Survey of Student Engagements, students spend on average 17 hours per week reviewing and practicing material previously learned in a classroom, with higher performing students showing a tendency to spend more time practicing. As such, learning software has emerged in the past several decades focusing on providing a wide range of examples, practice problems, and situations for users to exercise their skills. Notably, math students have benefited from software that procedurally generates a virtually infinite number of practice problems and their corresponding solutions. This allows for instantaneous feedback and automatic generation of tests and quizzes. Of course, this is only possible because software is capable of generating and verifying a virtually endless supply of sample problems across a wide range of topics within mathematics. While English learning software has progressed in a similar manner, it faces a series of hurdles distinctly different from those of mathematics. In particular, there is a wide range of exception cases present in English grammar. Some words have unique spellings for their plural forms, some words have identical spelling for plural forms, and some words are conjugated differently for only one particular tense or person-of-speech. These issues combined make the problem of generating grammatically correct sentences complicated. To compound to this problem, the grammar rules in English are vast, and often depend on the context in which they are used. Verb-tense agreement (e.g. "I eat" vs "he eats"), and conjugation of irregular verbs (e.g. swim -> swam) are common examples. This thesis presents an algorithm designed to randomly generate a virtually infinite number of practice problems for students of English as a second language. This approach differs from other generation approaches by generating based on a context set by educators, so that problems can be generated in the context of what students are currently learning. The algorithm is validated through a study in which over 35 000 sentences generated by the algorithm are verified by multiple grammar checking algorithms, and a subset of the sentences are validated against 3 education standards by a subject matter expert in the field. The study found that this approach has a significantly reduced grammar error ratio compared to other generation algorithms, and shows potential where context specification is concerned.
ContributorsMoore, Zachary Christian (Author) / Amresh, Ashish (Thesis director) / Nelson, Brian (Committee member) / Software Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Natural Language Processing is a subject that combines computer science and linguistics, aiming to provide computers with the ability to understand natural language and to develop a more intuitive human-computer interaction. The research community has developed ways to translate natural language to mathematical formalisms. It has not yet been shown, however, how to automatically translate different kinds of knowledge in English to distinct formal languages. Most of the recent work presents the problem that the translation method aims to a specific formal language or is hard to generalize. In this research, I take a first step to overcome this difficulty and present two algorithms which take as input two lambda-calculus expressions G and H and compute a lambda-calculus expression F. The expression F returned by the first algorithm satisfies F@G=H and, in the case of the second algorithm, we obtain G@F=H. The lambda expressions represent the meanings of words and sentences. For each formal language that one desires to use with the algorithms, the language must be defined in terms of lambda calculus. Also, some additional concepts must be included. After doing this, given a sentence, its representation and knowing the representation of several words in the sentence, the algorithms can be used to obtain the representation of the other words in that sentence. In this work, I define two languages and show examples of their use with the algorithms. The algorithms are illustrated along with soundness and completeness proofs, the latter with respect to typed lambda-calculus formulas up to the second order. These algorithms are a core part of a natural language semantics system that translates sentences from English to formulas in different formal languages.
ContributorsAlvarez Gonzalez, Marcos (Author) / Baral, Chitta (Thesis advisor) / Lee, Joohyung (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2010
Description
Goal specification is an important aspect of designing autonomous agents. A goal does not only refer to the set of states for the agent to reach. A goal also defines restrictions on the paths the agent should follow. Temporal logics are widely used in goal specification. However, they lack the ability to represent goals in a non-deterministic domain, goals that change non-monotonically, and goals with preferences. This dissertation defines new goal specification languages by extending temporal logics to address these issues. First considered is the goal specification in non-deterministic domains, in which an agent following a policy leads to a set of paths. A logic is proposed to distinguish paths of the agent from all paths in the domain. In addition, to address the need of comparing policies for finding the best ones, a language capable of quantifying over policies is proposed. As policy structures of agents play an important role in goal specification, languages are also defined by considering different policy structures. Besides, after an agent is given an initial goal, the agent may change its expectations or the domain may change, thus goals that are previously specified may need to be further updated, revised, partially retracted, or even completely changed. Non-monotonic goal specification languages that can make these changes in an elaboration tolerant manner are needed. Two languages that rely on labeling sub-formulas and connecting multiple rules are developed to address non-monotonicity in goal specification. Also, agents may have preferential relations among sub-goals, and the preferential relations may change as agents achieve other sub-goals. By nesting a comparison operator with other temporal operators, a language with dynamic preferences is proposed. Various goals that cannot be expressed in other languages are expressed in the proposed languages. Finally, plans are given for some goals specified in the proposed languages.
ContributorsZhao, Jicheng (Author) / Baral, Chitta (Thesis advisor) / Kambhampati, Subbarao (Committee member) / Lee, Joohyung (Committee member) / Lifschitz, Vladimir (Committee member) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2010
Description
One of the core components of many video games is their artificial intelligence. Through AI, a game can tell stories, generate challenges, and create encounters for the player to overcome. Even though AI has continued to advance through the implementation of neural networks and machine learning, game AI tends to implement a series of states or decisions instead to give the illusion of intelligence. Despite this limitation, games can still generate a wide range of experiences for the player. The Hybrid Game AI Framework is an AI system that combines the benefits of two commonly used approaches to developing game AI: Behavior Trees and Finite State Machines. Developed in the Unity Game Engine and the C# programming language, this AI Framework represents the research that went into studying modern approaches to game AI and my own attempt at implementing the techniques learned. Object-oriented programming concepts such as inheritance, abstraction, and low coupling are utilized with the intent to create game AI that's easy to implement and expand upon. The final goal was to create a flexible yet structured AI data structure while also minimizing drawbacks by combining Behavior Trees and Finite State Machines.
ContributorsRamirez Cordero, Erick Alberto (Author) / Kobayashi, Yoshihiro (Thesis director) / Nelson, Brian (Committee member) / Computer Science and Engineering Program (Contributor) / Computing and Informatics Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
This thesis investigates students' learning behaviors through their interaction with an educational technology, Web Programming Grading Assistant. The technology was developed to facilitate the grading of paper-based examinations in large lecture-based classrooms and to provide richer and more meaningful feedback to students. A classroom study was designed and data was gathered from an undergraduate computer-programming course in the fall of 2016. Analysis of the data revealed that there was a negative correlation between time lag of first review attempt and performance. A survey was developed and disseminated that gave insight into how students felt about the technology and what they normally do to study for programming exams. In conclusion, the knowledge gained in this study aids in the quest to better educate students in computer programming in large in-person classrooms.
ContributorsMurphy, Hannah (Author) / Hsiao, Ihan (Thesis director) / Nelson, Brian (Committee member) / School of Computing, Informatics, and Decision Systems Engineering (Contributor) / Department of Supply Chain Management (Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
Description
This research lays down foundational work in the semantic reconstruction of linguistic politeness in English-to-Japanese machine translation and thereby advances semantic-based automated translation of English into other natural languages. I developed a Java project called the PoliteParser that is intended as a plug-in to existing semantic parsers to determine whether verbs in dialogue in an English corpus should be conjugated into the plain or the polite honorific form when translated into Japanese. The PoliteParser bases this decision off of semantic information about the social relationships between the speaker and the listener, the speaker's personality, and the circumstances of the utterance. Testing undergone during the course of this research demonstrates that the PoliteParser can achieve levels of accuracy 31 percentage points higher than that of statistical translation systems when integrated with a semantic parser and 54 percentage points higher when used with pre-parsed data.
ContributorsGuiou, Jared Tyler (Author) / Baral, Chitta (Thesis director) / Tanno, Koji (Committee member) / School of International Letters and Cultures (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12
Description
Can a skill taught in a virtual environment be utilized in the physical world? This idea is explored by creating a Virtual Reality game for the HTC Vive to teach users how to play the drums. The game focuses on developing the user's muscle memory, improving the user's ability to play music as they hear it in their head, and refining the user's sense of rhythm. Several different features were included to achieve this such as a score, different levels, a demo feature, and a metronome. The game was tested for its ability to teach and for its overall enjoyability by using a small sample group. Most participants of the sample group noted that they felt as if their sense of rhythm and drumming skill level would improve by playing the game. Through the findings of this project, it can be concluded that while it should not be considered as a complete replacement for traditional instruction, a virtual environment can be successfully used as a learning aid and practicing tool.
ContributorsDinapoli, Allison (Co-author) / Tuznik, Richard (Co-author) / Kobayashi, Yoshihiro (Thesis director) / Nelson, Brian (Committee member) / Computer Science and Engineering Program (Contributor) / School of International Letters and Cultures (Contributor) / Computing and Informatics Program (Contributor) / Barrett, The Honors College (Contributor)
Created2017-12
Description
Machine learning models can pick up biases and spurious correlations from training data and projects and amplify these biases during inference, thus posing significant challenges in real-world settings. One approach to mitigating this is a class of methods that can identify filter out bias-inducing samples from the training datasets to force models to avoid being exposed to biases. However, the filtering leads to a considerable wastage of resources as most of the dataset created is discarded as biased. This work deals with avoiding the wastage of resources by identifying and quantifying the biases. I further elaborate on the implications of dataset filtering on robustness (to adversarial attacks) and generalization (to out-of-distribution samples). The findings suggest that while dataset filtering does help to improve OOD(Out-Of-Distribution) generalization, it has a significant negative impact on robustness to adversarial attacks. It also shows that transforming bias-inducing samples into adversarial samples (instead of eliminating them from the dataset) can significantly boost robustness without sacrificing generalization.
ContributorsSachdeva, Bhavdeep Singh (Author) / Baral, Chitta (Thesis advisor) / Liu, Huan (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2021
Description
Instructional prompts are a novel technique that can significantly improve the performance of natural language processing tasks by specifying the task instruction to the language model. This is the first paper that uses instructional prompts to improve performance of the question answering task in biomedical domain. This work makes two significant contributions. Firstly, a question answer dataset of 600K question answer pairs has been developed by using the medical textbook ‘Differential Diagnosis Primary Care’, which contains information on how to diagnose a patient by observing their disease symptoms. Secondly, a question answering language model augmented with instructional prompts has been developed by training on the medical information extracted from the book ‘Differential Diagnosis Primary Care’. Experiments have been conducted to demonstrate that it performs better than a normal question answering model that does not use instructional prompts. Instructional prompts are based on prompt tuning and prefix tuning, which are novel techniques which can help train language model to do specific downstream tasks by keeping majority of model parameters frozen, and only optimizing a small number of continuous task-specific vectors (called the prefixes).
ContributorsSaxena, Sharad (Author) / Baral, Chitta (Thesis advisor) / Blanco, Eduardo (Committee member) / Anwar, Saadat (Committee member) / Arizona State University (Publisher)
Created2021