Author: Antoine Bosselut Publisher: ISBN: Category : Languages : en Pages : 154
Book Description
For machines to understand language, they must intuitively grasp the commonsense knowledge that underlies the situations they encounter in text. A simple statement such as it is raining immediately implies a bank of shared context for any human reader: they should bring an umbrella, roads will be slippery, increased traffic may make them late, rain boots are preferable to sandals, and many more. Language understanding systems must be able to robustly use this commonsense knowledge to make decisions or take actions. Observations of the world are always more rich and detailed than the information that is explicitly transmitted through language, and machines must be able to fill in remaining details with commonsense inferences. Recent advances in natural language processing have made considerable progress in identifying the commonsense implications of situations described in text. These methods generally involve training high-parameter language models on large language corpora and have shown marked improvement on a variety of benchmark end tasks in natural language understanding. However, these systems are brittle 0́3 often failing when presented with out-of-distribution inputs -- and uninterpretable -- incapable of providing insights into why these different inputs cause shifted behavior. Meanwhile, traditional approaches to natural language understanding, which focus on linking language to background knowledge from large ontologies, remain limited by their inability to scale to the situational diversity expressed through language. In this dissertation, we argue that for natural language understanding agents to function in less controlled test environments, they must learn to reason more explicitly about the commonsense knowledge underlying textual situations. In furtherance of these goals, we draw from both traditional symbolic and modern neural approaches to natural language understanding. We present four studies on learning commonsense representations from language, and integrating and reasoning about these representations in NLP systems to achieve more robust textual understanding.
Author: Łucja M. Iwańska Publisher: AAAI Press ISBN: Category : Computers Languages : en Pages : 490
Book Description
"Traditionally, knowledge representation and reasoning systems have incorporated natural language as interfaces to expert systems or knowledge bases that performed tasks separate from natural language processing. As this book shows, however, the computational nature of representation and inference in natural language makes it the ideal model for all tasks in an intelligent computer system. Natural language processing combines the qualitative characteristics of human knowledge processing with a computer's quantitative advantages, allowing for in-depth, systematic processing of vast amounts of information.
Author: Arpit Sharma Publisher: ISBN: Category : Commonsense reasoning Languages : en Pages : 211
Book Description
Reasoning with commonsense knowledge is an integral component of human behavior. It is due to this capability that people know that a weak person may not be able to lift someone. It has been a long standing goal of the Artificial Intelligence community to simulate such commonsense reasoning abilities in machines. Over the years, many advances have been made and various challenges have been proposed to test their abilities. The Winograd Schema Challenge (WSC) is one such Natural Language Understanding (NLU) task which was also proposed as an alternative to the Turing Test. It is made up of textual question answering problems which require resolution of a pronoun to its correct antecedent. In this thesis, two approaches of developing NLU systems to solve the Winograd Schema Challenge are demonstrated. To this end, a semantic parser is presented, various kinds of commonsense knowledge are identified, techniques to extract commonsense knowledge are developed and two commonsense reasoning algorithms are presented. The usefulness of the developed tools and techniques is shown by applying them to solve the challenge.
Author: Kenneth D. Forbus Publisher: MIT Press ISBN: 0262349817 Category : Psychology Languages : en Pages : 441
Book Description
An argument that qualitative representations—symbolic representations that carve continuous phenomena into meaningful units—are central to human cognition. In this book, Kenneth Forbus proposes that qualitative representations hold the key to one of the deepest mysteries of cognitive science: how we reason and learn about the continuous phenomena surrounding us. Forbus argues that qualitative representations—symbolic representations that carve continuous phenomena into meaningful units—are central to human cognition. Qualitative representations provide a basis for commonsense reasoning, because they enable practical reasoning with very little data; this makes qualitative representations a useful component of natural language semantics. Qualitative representations also provide a foundation for expert reasoning in science and engineering by making explicit the broad categories of things that might happen and enabling causal models that help guide the application of more quantitative knowledge as needed. Qualitative representations are important for creating more human-like artificial intelligence systems with capabilities for spatial reasoning, vision, question answering, and understanding natural language. Forbus discusses, among other topics, basic ideas of knowledge representation and reasoning; qualitative process theory; qualitative simulation and reasoning about change; compositional modeling; qualitative spatial reasoning; and learning and conceptual change. His argument is notable both for presenting an approach to qualitative reasoning in which analogical reasoning and learning play crucial roles and for marshaling a wide variety of evidence, including the performance of AI systems. Cognitive scientists will find Forbus's account of qualitative representations illuminating; AI scientists will value Forbus's new approach to qualitative representations and the overview he offers.
Author: Hermann Helbig Publisher: Springer Science & Business Media ISBN: 3540299661 Category : Computers Languages : en Pages : 652
Book Description
Natural Language is not only the most important means of communication between human beings, it is also used over historical periods for the pres- vation of cultural achievements and their transmission from one generation to the other. During the last few decades, the ?ood of digitalized information has been growing tremendously. This tendency will continue with the globali- tion of information societies and with the growing importance of national and international computer networks. This is one reason why the theoretical und- standing and the automated treatment of communication processes based on natural language have such a decisive social and economic impact. In this c- text, the semantic representation of knowledge originally formulated in natural language plays a central part, because it connects all components of natural language processing systems, be they the automatic understanding of natural language (analysis), the rational reasoning over knowledge bases, or the g- eration of natural language expressions from formal representations. This book presents a method for the semantic representation of natural l- guage expressions (texts, sentences, phrases, etc. ) which can be used as a u- versal knowledge representation paradigm in the human sciences, like lingu- tics, cognitive psychology, or philosophy of language, as well as in com- tational linguistics and in arti?cial intelligence. It is also an attempt to close the gap between these disciplines, which to a large extent are still working separately.
Author: American Association for Artificial Intelligence Publisher: ISBN: 9780262510578 Category : Computers Languages : en Pages : 596
Book Description
AAAI proceedings describe innovative concepts, techniques, perspectives, and observations that present promising research directions in artificial intelligence.AI and Education. Automated Reasoning: automatic programming, planning and scheduling, rule-based reasoning, search, theorem proving, uncertainty, truth-maintenance systems, constraint-based systems. Cognitive Modeling. Commonsense Reasoning: qualitative reasoning, design, diagnosis, simulation. Impacts of AI Technology: organizational, economic, and social implications. Knowledge Acquisition and Expert System Design Methodologies: techniques for designing expert systems and acquiring domain knowledge. Knowledge Representation: knowledge-representation systems, inheritance, nonmonotonic logic, nonstandard logics, temporal reasoning. Machine Architectures and Computer Languages for AI. Machine Learning. Natural Language: generation and understanding; syntax, speech, dialogue. Perception and Signal Understanding: vision. Philosophical Foundations. Robotics. User Interfaces.
Author: Philip C. Jackson Publisher: Courier Dover Publications ISBN: 0486845206 Category : Mathematics Languages : en Pages : 386
Book Description
Dr. Jackson discusses how an AI system using a language of thought based on the unconstrained syntax of a natural language could achieve "higher-level mentalities" of human intelligence, with advanced forms of learning and reasoning, imagination, and more. 2019 edition.
Author: Frank van Harmelen Publisher: Elsevier ISBN: 0080557023 Category : Computers Languages : en Pages : 1035
Book Description
Handbook of Knowledge Representation describes the essential foundations of Knowledge Representation, which lies at the core of Artificial Intelligence (AI). The book provides an up-to-date review of twenty-five key topics in knowledge representation, written by the leaders of each field. It includes a tutorial background and cutting-edge developments, as well as applications of Knowledge Representation in a variety of AI systems. This handbook is organized into three parts. Part I deals with general methods in Knowledge Representation and reasoning and covers such topics as classical logic in Knowledge Representation; satisfiability solvers; description logics; constraint programming; conceptual graphs; nonmonotonic reasoning; model-based problem solving; and Bayesian networks. Part II focuses on classes of knowledge and specialized representations, with chapters on temporal representation and reasoning; spatial and physical reasoning; reasoning about knowledge and belief; temporal action logics; and nonmonotonic causal logic. Part III discusses Knowledge Representation in applications such as question answering; the semantic web; automated planning; cognitive robotics; multi-agent systems; and knowledge engineering. This book is an essential resource for graduate students, researchers, and practitioners in knowledge representation and AI. * Make your computer smarter* Handle qualitative and uncertain information* Improve computational tractability to solve your problems easily
Author: Antoine Bosselut
Author: Łucja M. Iwańska
Author: Arpit Sharma
Author: Kenneth D. Forbus
Author: Meng Jiang
Author: Hermann Helbig
Author: Leonard Bolc
Author: American Association for Artificial Intelligence
Author: Philip C. Jackson
Author: Frank van Harmelen