Thesis (Ph. D.)--University of Texas at Austin, 2000. / Vita. Includes bibliographical references (leaves 230-235). Available also in a digital version from Dissertation Abstracts.

Bibliography: p. 121-125. / xiv, 125 p. ; 30 cm. / Title page, contents and abstract only. The complete thesis in print form is available from the University Library. / One of the central issues in Artificial Intelligence (AI) is common sense reasoning. This includes logics of knowledge and belief, non-monotonic reasoning, truth-maintenance and belief revision. Within these fields the notion of a consistent belief state is the crucial one. The issues of inconsistency and partiality of information are central to this thesis which proposes a logical knowledge representation formalism employing partial objects and partial worlds on its semantic side. The syntax includes a language, formulae, and partial theories. Partial worlds and theories are consistent, and contradictory information is assumed to arise in multiple agent situations. Relevant mathematical structures are discussed, in particular partial theories are related to partial worlds. A multiple agent case is considered. Partial theories can be partially ordered by an information ordering and the obtained lattice structure facilitates the theory selection process based on information value and truthness of theories. / Thesis (Ph.D.)--University of Adelaide, Dept. of Computer Science, 1998

Bibliography: p. 121-125. / xiv, 125 p. ; 30 cm. / Title page, contents and abstract only. The complete thesis in print form is available from the University Library. / One of the central issues in Artificial Intelligence (AI) is common sense reasoning. This includes logics of knowledge and belief, non-monotonic reasoning, truth-maintenance and belief revision. Within these fields the notion of a consistent belief state is the crucial one. The issues of inconsistency and partiality of information are central to this thesis which proposes a logical knowledge representation formalism employing partial objects and partial worlds on its semantic side. The syntax includes a language, formulae, and partial theories. Partial worlds and theories are consistent, and contradictory information is assumed to arise in multiple agent situations. Relevant mathematical structures are discussed, in particular partial theories are related to partial worlds. A multiple agent case is considered. Partial theories can be partially ordered by an information ordering and the obtained lattice structure facilitates the theory selection process based on information value and truthness of theories. / Thesis (Ph.D.)--University of Adelaide, Dept. of Computer Science, 1998

Thesis (Ph.D.)--University of Adelaide, Dept. of Computer Science, 1998. / Bibliography: p. 121-125.

Thesis (Ph. D.)--University of Washington, 2008. / Vita. Includes bibliographical references (p. 105-112).

Thesis (Ph.D.)--Duquesne University, 2005. / Title from document title page. Abstract included in electronic submission form. Includes bibliographical references (p. 196-204) and index.

Artificial Intelligence (AI) technologies are increasingly pervading aspects of our lives. Because people use natural language to communicate with each other, computers should also use natural language to communicate with us. One of the principal obstacles to achieving this is the ambiguity of natural language, evidenced in problems such as prepositional phrase attachment and pronoun coreference. Current methods rely on the statistical frequency of word patterns, but this is often brittle and opaque to people. In this thesis, I explore the idea of using commonsense knowledge to resolve linguistic ambiguities. I introduce PatchComm, which invokes explicit commonsense assertions to solve context-independent ambiguities. When commonsense assertions are missing, I invoke RetroGAN-DRD, which leverages state-of-the-art inference techniques such as retrofitting and generative adversarial networks (GAN) to infer commonsense assertions. I build upon that with ProGeneXP, which brings state-of-the-art language models to the task of describing its inputs and implicit knowledge in natural language while providing meaningful descriptions for PatchComm to align to further resolve linguistic ambiguities. Finally, I introduce DialComm to lay the groundwork for moving from single-sentence disambiguation to discourse. Specifically, DialComm builds upon PatchComm to obtain information from single sentences and integrates such information with additional commonsense assertions to build integral frame representations for discourses. I illustrate DialComm’s ability with an application to end-user programming in natural language. The contributions of this dissertation lie in showing how commonsense inference can be integrated with parsing to resolve ambiguities in natural language, in a transparent manner. I have implemented three candidate systems, with increasingly sophisticated approaches. I verified that they perform well on some standard tests, and they operate in such a way that is understandable to people. This obviates the mythical inevitability of an interpretability-performance tradeoff. I have shown how my techniques can be used in a candidate application, programming in natural language. My work leaves us in a good position to exploit further advances in natural language understanding and commonsense inference. I am optimistic that natural, transparent communication with computers will help make the world a better place.

Chiu, Yiu Man Edmund. / Thesis submitted in: December 1999. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2000. / Includes bibliographical references (leaves 269-248). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgments --- p.iii / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- The Beginning Story --- p.2 / Chapter 1.2 --- Background --- p.3 / Chapter 1.2.1 --- History of Nonmonotonic Reasoning --- p.3 / Chapter 1.2.2 --- Formalizations of Nonmonotonic Reasoning --- p.6 / Chapter 1.2.3 --- Belief Revision --- p.13 / Chapter 1.2.4 --- Network Representation of Knowledge --- p.17 / Chapter 1.2.5 --- Reference from Logic Programming --- p.21 / Chapter 1.2.6 --- Recent Work on Network-type Automatic Reasoning Sys- tems --- p.22 / Chapter 1.3 --- A Novel Inference Network Approach --- p.23 / Chapter 1.4 --- Objectives --- p.23 / Chapter 1.5 --- Organization of the Thesis --- p.24 / Chapter 2 --- The Predicate Inference Network PIN --- p.25 / Chapter 2.1 --- Preliminary Terms --- p.26 / Chapter 2.2 --- Overall Structure --- p.27 / Chapter 2.3 --- Object Layer --- p.29 / Chapter 2.3.1 --- Virtual Object --- p.31 / Chapter 2.4 --- Predicate Layer --- p.33 / Chapter 2.4.1 --- Node Values --- p.34 / Chapter 2.4.2 --- Information Source --- p.35 / Chapter 2.4.3 --- Belief State --- p.36 / Chapter 2.4.4 --- Predicates --- p.37 / Chapter 2.4.5 --- Prototypical Predicates --- p.37 / Chapter 2.4.6 --- Multiple Inputs for a Single Belief --- p.39 / Chapter 2.4.7 --- External Program Call --- p.39 / Chapter 2.5 --- Variable Layer --- p.40 / Chapter 2.6 --- Inter-Layer Links --- p.42 / Chapter 2.7 --- Chapter Summary --- p.43 / Chapter 3 --- Computation for PIN --- p.44 / Chapter 3.1 --- Computation Functions for Propagation --- p.45 / Chapter 3.1.1 --- Computational Functions for Combinative Links --- p.45 / Chapter 3.1.2 --- Computational Functions for Alternative Links --- p.49 / Chapter 3.2 --- Applying the Computation Functions --- p.52 / Chapter 3.3 --- Relations Represented in PIN --- p.55 / Chapter 3.3.1 --- Relations Represented by Combinative Links --- p.56 / Chapter 3.3.2 --- Relations Represented by Alternative Links --- p.59 / Chapter 3.4 --- Chapter Summary --- p.61 / Chapter 4 --- Dynamic Knowledge Update --- p.62 / Chapter 4.1 --- Operations for Knowledge Update --- p.63 / Chapter 4.2 --- Logical Expression --- p.63 / Chapter 4.3 --- Applicability of Operators --- p.64 / Chapter 4.4 --- Add Operation --- p.65 / Chapter 4.4.1 --- Add a fully instantiated single predicate proposition with no virtual object --- p.66 / Chapter 4.4.2 --- Add a fully instantiated pure disjunction --- p.68 / Chapter 4.4.3 --- Add a fully instantiated expression which is a conjunction --- p.71 / Chapter 4.4.4 --- Add a human biased relation --- p.74 / Chapter 4.4.5 --- Add a single predicate expression with virtual objects --- p.76 / Chapter 4.4.6 --- Add a IF-THEN rule --- p.80 / Chapter 4.5 --- Remove Operation --- p.88 / Chapter 4.5.1 --- Remove a Belief --- p.88 / Chapter 4.5.2 --- Remove a Rule --- p.91 / Chapter 4.6 --- Revise Operation --- p.94 / Chapter 4.6.1 --- Revise a Belief --- p.94 / Chapter 4.6.2 --- Revise a Rule --- p.96 / Chapter 4.7 --- Consistency Maintenance --- p.97 / Chapter 4.7.1 --- Logical Suppression --- p.98 / Chapter 4.7.2 --- Example on Handling Inconsistent Information --- p.99 / Chapter 4.8 --- Chapter Summary --- p.102 / Chapter 5 --- Knowledge Query --- p.103 / Chapter 5.1 --- Domains of Quantification --- p.104 / Chapter 5.2 --- Reasoning through Recursive Rules --- p.109 / Chapter 5.2.1 --- Infinite Looping Control --- p.110 / Chapter 5.2.2 --- Proof of the finite termination of recursive rules --- p.111 / Chapter 5.3 --- Query Functions --- p.117 / Chapter 5.4 --- Type I Queries --- p.119 / Chapter 5.4.1 --- Querying a Simple Single Predicate Proposition (Type I) --- p.122 / Chapter 5.4.2 --- Querying a Belief with Logical Connective(s) (Type I) --- p.128 / Chapter 5.5 --- Type II Queries --- p.132 / Chapter 5.5.1 --- Querying Single Predicate Expressions (Type II) --- p.134 / Chapter 5.5.2 --- Querying an Expression with Logical Connectives (Type II) --- p.143 / Chapter 5.6 --- Querying an Expression with Virtual Objects --- p.152 / Chapter 5.6.1 --- Type I Queries Involving Virtual Object --- p.152 / Chapter 5.6.2 --- Type II Queries involving Virtual Objects --- p.156 / Chapter 5.7 --- Chapter Summary --- p.157 / Chapter 6 --- Uniqueness and Finite Termination --- p.159 / Chapter 6.1 --- Proof Structure --- p.160 / Chapter 6.2 --- Proof for Completeness and Finite Termination of Domain Search- ing Procedure --- p.161 / Chapter 6.3 --- Proofs for Type I Queries --- p.167 / Chapter 6.3.1 --- Proof for Single Predicate Expressions --- p.167 / Chapter 6.3.2 --- Proof of Type I Queries on Expressions with Logical Con- nectives --- p.172 / Chapter 6.3.3 --- General Proof for Type I Queries --- p.174 / Chapter 6.4 --- Proofs for Type II Queries --- p.175 / Chapter 6.4.1 --- Proof for Type II Queries on Single Predicate Expressions --- p.176 / Chapter 6.4.2 --- Proof for Type II Queries on Disjunctions --- p.178 / Chapter 6.4.3 --- Proof for Type II Queries on Conjunctions --- p.179 / Chapter 6.4.4 --- General Proof for Type II Queries --- p.181 / Chapter 6.5 --- Proof for Queries Involving Virtual Objects --- p.182 / Chapter 6.6 --- Uniqueness and Finite Termination of PIN Queries --- p.183 / Chapter 6.7 --- Chapter Summary --- p.184 / Chapter 7 --- Lifschitz's Benchmark Problems --- p.185 / Chapter 7.1 --- Structure --- p.186 / Chapter 7.2 --- Default Reasoning --- p.186 / Chapter 7.2.1 --- Basic Default Reasoning --- p.186 / Chapter 7.2.2 --- Default Reasoning with Irrelevant Information --- p.187 / Chapter 7.2.3 --- Default Reasoning with Several Defaults --- p.188 / Chapter 7.2.4 --- Default Reasoning with a Disabled Default --- p.190 / Chapter 7.2.5 --- Default Reasoning in Open Domain --- p.191 / Chapter 7.2.6 --- Reasoning about Unknown Exceptions I --- p.193 / Chapter 7.2.7 --- Reasoning about Unknown Exceptions II --- p.194 / Chapter 7.2.8 --- Reasoning about Unknown Exceptions III --- p.196 / Chapter 7.2.9 --- Priorities between Defaults --- p.198 / Chapter 7.2.10 --- Priorities between Instances of a Default --- p.199 / Chapter 7.2.11 --- Reasoning about Priorities --- p.199 / Chapter 7.3 --- Inheritance --- p.200 / Chapter 7.3.1 --- Linear Inheritance --- p.200 / Chapter 7.3.2 --- Tree-Structured Inheritance --- p.202 / Chapter 7.3.3 --- One-Step Multiple Inheritance --- p.203 / Chapter 7.3.4 --- Multiple Inheritance --- p.204 / Chapter 7.4 --- Uniqueness of Names --- p.205 / Chapter 7.4.1 --- Unique Names Hypothesis for Objects --- p.205 / Chapter 7.4.2 --- Unique Names Hypothesis for Functions --- p.206 / Chapter 7.5 --- Reasoning about Action --- p.206 / Chapter 7.6 --- Autoepistemic Reasoning --- p.206 / Chapter 7.6.1 --- Basic Autoepistemic Reasoning --- p.206 / Chapter 7.6.2 --- Autoepistemic Reasoning with Incomplete Information --- p.207 / Chapter 7.6.3 --- Autoepistemic Reasoning with Open Domain --- p.207 / Chapter 7.6.4 --- Autoepistemic Default Reasoning --- p.208 / Chapter 8 --- Comparison with PROLOG --- p.214 / Chapter 8.1 --- Introduction of PROLOG --- p.215 / Chapter 8.1.1 --- Brief History --- p.215 / Chapter 8.1.2 --- Structure and Inference --- p.215 / Chapter 8.1.3 --- Why Compare PIN with Prolog --- p.216 / Chapter 8.2 --- Representation Power --- p.216 / Chapter 8.2.1 --- Close World Assumption and Negation as Failure --- p.216 / Chapter 8.2.2 --- Horn Clauses --- p.217 / Chapter 8.2.3 --- Quantification --- p.218 / Chapter 8.2.4 --- Build-in Functions --- p.219 / Chapter 8.2.5 --- Other Representation Issues --- p.220 / Chapter 8.3 --- Inference and Query Processing --- p.220 / Chapter 8.3.1 --- Unification --- p.221 / Chapter 8.3.2 --- Resolution --- p.222 / Chapter 8.3.3 --- Computation Efficiency --- p.225 / Chapter 8.4 --- Knowledge Updating and Consistency Issues --- p.227 / Chapter 8.4.1 --- PIN and AGM Logic --- p.228 / Chapter 8.4.2 --- Knowledge Merging --- p.229 / Chapter 8.5 --- Chapter Summary --- p.229 / Chapter 9 --- Conclusion and Discussion --- p.230 / Chapter 9.1 --- Conclusion --- p.231 / Chapter 9.1.1 --- General Structure --- p.231 / Chapter 9.1.2 --- Representation Power --- p.231 / Chapter 9.1.3 --- Inference --- p.232 / Chapter 9.1.4 --- Dynamic Update and Consistency --- p.233 / Chapter 9.1.5 --- Soundness and Completeness Versus Efficiency --- p.233 / Chapter 9.2 --- Discussion --- p.234 / Chapter 9.2.1 --- Different Selection Criteria --- p.234 / Chapter 9.2.2 --- Link Order --- p.235 / Chapter 9.2.3 --- Inheritance Reasoning --- p.236 / Chapter 9.3 --- Future Work --- p.237 / Chapter 9.3.1 --- Implementation --- p.237 / Chapter 9.3.2 --- Application --- p.237 / Chapter 9.3.3 --- Probabilistic and Fuzzy PIN --- p.238 / Chapter 9.3.4 --- Temporal Reasoning --- p.238 / Bibliography --- p.239

abstract: Image Understanding is a long-established discipline in computer vision, which encompasses a body of advanced image processing techniques, that are used to locate (“where”), characterize and recognize (“what”) objects, regions, and their attributes in the image. However, the notion of “understanding” (and the goal of artificial intelligent machines) goes beyond factual recall of the recognized components and includes reasoning and thinking beyond what can be seen (or perceived). Understanding is often evaluated by asking questions of increasing difficulty. Thus, the expected functionalities of an intelligent Image Understanding system can be expressed in terms of the functionalities that are required to answer questions about an image. Answering questions about images require primarily three components: Image Understanding, question (natural language) understanding, and reasoning based on knowledge. Any question, asking beyond what can be directly seen, requires modeling of commonsense (or background/ontological/factual) knowledge and reasoning. Knowledge and reasoning have seen scarce use in image understanding applications. In this thesis, we demonstrate the utilities of incorporating background knowledge and using explicit reasoning in image understanding applications. We first present a comprehensive survey of the previous work that utilized background knowledge and reasoning in understanding images. This survey outlines the limited use of commonsense knowledge in high-level applications. We then present a set of vision and reasoning-based methods to solve several applications and show that these approaches benefit in terms of accuracy and interpretability from the explicit use of knowledge and reasoning. We propose novel knowledge representations of image, knowledge acquisition methods, and a new implementation of an efficient probabilistic logical reasoning engine that can utilize publicly available commonsense knowledge to solve applications such as visual question answering, image puzzles. Additionally, we identify the need for new datasets that explicitly require external commonsense knowledge to solve. We propose the new task of Image Riddles, which requires a combination of vision, and reasoning based on ontological knowledge; and we collect a sufficiently large dataset to serve as an ideal testbed for vision and reasoning research. Lastly, we propose end-to-end deep architectures that can combine vision, knowledge and reasoning modules together and achieve large performance boosts over state-of-the-art methods. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2018

abstract: Significance of real-world knowledge for Natural Language Understanding(NLU) is well-known for decades. With advancements in technology, challenging tasks like question-answering, text-summarizing, and machine translation are made possible with continuous efforts in the field of Natural Language Processing(NLP). Yet, knowledge integration to answer common sense questions is still a daunting task. Logical reasoning has been a resort for many of the problems in NLP and has achieved considerable results in the field, but it is difficult to resolve the ambiguities in a natural language. Co-reference resolution is one of the problems where ambiguity arises due to the semantics of the sentence. Another such problem is the cause and result statements which require causal commonsense reasoning to resolve the ambiguity. Modeling these type of problems is not a simple task with rules or logic. State-of-the-art systems addressing these problems use a trained neural network model, which claims to have overall knowledge from a huge trained corpus. These systems answer the questions by using the knowledge embedded in their trained language model. Although the language models embed the knowledge from the data, they use occurrences of words and frequency of co-existing words to solve the prevailing ambiguity. This limits the performance of language models to solve the problems in common-sense reasoning task as it generalizes the concept rather than trying to answer the problem specific to its context. For example, "The painting in Mark's living room shows an oak tree. It is to the right of a house", is a co-reference resolution problem which requires knowledge. Language models can resolve whether "it" refers to "painting" or "tree", since "house" and "tree" are two common co-occurring words so the models can resolve "tree" to be the co-reference. On the other hand, "The large ball crashed right through the table. Because it was made of Styrofoam ." to resolve for "it" which can be either "table" or "ball", is difficult for a language model as it requires more information about the problem. In this work, I have built an end-to-end framework, which uses the automatically extracted knowledge based on the problem. This knowledge is augmented with the language models using an explicit reasoning module to resolve the ambiguity. This system is built to improve the accuracy of the language models based approaches for commonsense reasoning. This system has proved to achieve the state of the art accuracy on the Winograd Schema Challenge. / Dissertation/Thesis / Masters Thesis Computer Science 2019