In the twenty years from first grade to a PhD, students never learn any subject by the methods for which machine-learning algorithms have been designed.Those algorithms are useful for analyzing large volumes of data.But they don't enable a computer system to learn a language as quickly and accurately as a three-year-old child.They're not even as effective as a mother raccoon teaching her babies how to find the best garbage cans.For all animals, learning is integrated with the cognitive cycle from perception to purposeful action.Many algorithms are needed to support that cycle.But an intelligent system must be more than a collection of algorithms.It must integrate them in a cognitive cycle of perception, learning, reasoning, and action.That cycle is key to designing intelligent systems. I. THEORIES OF LEARNING AND REASONINGHE nature of the knowledge stored in our heads has major implications for educating children and for designing intelligent systems.Both fields organize knowledge in teachable modules that are presented in textbooks and stored in well structured databases and knowledge bases.A systematic organization makes knowledge easier to teach and to implement in computer systems.But as every student discovers upon entering the workforce, "book learning" is limited by the inevitable complexities, exceptions, and ambiguities of engineering, business, politics, and life.Although precise definitions and specifications are essential for solving problems in mathematics, science, and engineering, most problems aren't well defined.As Shakespeare observed, "There are more things in heaven and earth, Horatio, than are dreamt of in your philosophy." The Cognitive Cycle

Revelator has been designed as a game for improving collaborative inquiry, in a format that resembles familiar intellectual games, such as bridge, crossword puzzles, poker, and chess. Its purpose is to reveal the complex relations among conditional propositions, which players use to represent their conjectures as plays in the game. Plays in Revelator become players' 'logical agents' that attempt to adapt within complex conceptual environments. Revelator's design provides a context for computer agent technologies (including Semantic Web, Conceptual Graphs, ISO Common Logic, and other approaches) to evolve in iterative cycles of empirical testing, evaluation, and advancement. The game can be used to challenge knowledge capture technology in tournaments to improve capabilities that support the progress of inquiry.

Margaret Masterman was one of six students in Wittgenstein's course of [1933][1934] whose notes were compiled as The Blue Book (Wittgenstein 1958, which is the first publication after the mimeographed copies that were circulated informally).In the late 1950s, she founded the Cambridge Language Research Unit (CLRU) as a discussion group, which evolved into one of the pioneering centers of research in computational linguistics.In her will, she requested that Yorick Wilks edit a collection of her papers for publication.The result is this book, which is important for its historical perspective on the development of computational linguistics.It consists of 11 of her reports and articles from the late 1950s to 1980 and includes a 17-page introduction and commentary by Wilks.Karen Spärck Jones also wrote a commentary on one of the papers she had coauthored.As a student of Wittgenstein, Masterman was also deeply concerned about the foundations of theoretical linguistics.Around the same time that Chomsky was developing his syntactic theories and Montague was advocating a logic-based alternative, she was proposing a "neo-Wittgensteinian" view, whose organizing principle was a thesaurus of words classified according to the "language games" in which they are used.Although no single paper in the book formulates a succinct summary that could be called a theory, the following principles are discussed throughout:

In this book, Nirenburg and Raskin present an important body of work in computational linguistics that they and their colleagues have been developing over the past 20 years.For a unifying perspective, they organize their assumptions, theories, and techniques around the theme of ontological semantics.Along the way, they critique many alternative views of semantics, which they distinguish from their own.Their analyses contribute to a much-needed debate about the history and future of computational linguistics, but to preserve some balance, teachers and students should keep a few of the alternatives on their reference shelf.The book is divided into two parts: a philosophical part I and a practical part II.The first part consists of an introductory chapter 1 and four chapters that survey important but controversial issues about linguistics, both theoretical and computational.In those chapters, the authors make a good case for their version of ontological semantics, but the alternatives are not treated in detail.In part II, the authors present their text-meaning representation (TMR) and demonstrate how it is used in language analysis.Any discussion of technical material must use some notation, and TMR is sufficiently flexible to illustrate a wide range of semantic-based methods that could be adapted to many other formalisms.For most readers, part II would be the more important.Chapter 1 is a good 25-page overview of computational linguistics with an emphasis on semantics.Students and novices, however, need examples, and none are given until chapter 6.The authors suggest that ''a well-prepared and/or uninterested reader'' skip the remainder of part I and go straight to chapter 6, which begins with an excellent five-page example.The authors follow that advice when they teach courses from this text.In Chapter 2, the authors present their ''Prolegomena to the Philosophy of Linguistics.''Their ideas are well taken, and some are as old as Socrates: Examine the assumptions, challenge conventional wisdom, and test conclusions against experience.The basis of their approach is what they call the four components of a scientific theory:1.The purview of a theory is ''the set of phenomena for which the theory holds itself-and is held-accountable.''2. The premises are belief statements ''taken for granted by the theory and not addressed in its body.

Object-oriented programming languages are designed for computing or simulating the behaviour of interacting objects, but their encapsulated contexts and procedural methods are not well suited to non-procedural techniques in theorem provers, optimizers, and automated design and analysis tools. Logic is the non-procedural system par excellence, but the predicate calculus notation for logic is awkward for representing and reasoning about encapsulated contexts. Conceptual graphs are a graphic system of logic that is better suited to O-O systems. First, they explicitly represent the contexts that are ignored or obscured in predicate calculus. Second, Peirce's rules of inference for reasoning with graphs are explicitly formulated in terms of contexts and the conditions for importing and exporting information from contexts. This article describes the context mechanisms of conceptual graphs, the rules of inference for reasoning with the graphs, and their use as a design language for object-oriented systems.

Conceptual graphs are both a language for representing knowledge and patterns for constructing models. They form models in the AI sense of structures that approximate some actual or possible system in the real world. They also form models in the logical sense of structures for which some set of axioms are true. When combined with recent developments in nonstandard logic and semantics, conceptual graphs can form a bridge between heuristic techniques of AI and formal techniques of model theory.