Government
Learning Syntactic Patterns for Automatic Hypernym Discovery
Snow, Rion, Jurafsky, Daniel, Ng, Andrew Y.
Semantic taxonomies such as WordNet provide a rich source of knowledge fornatural language processing applications, but are expensive to build, maintain, and extend. Motivated by the problem of automatically constructing and extending such taxonomies, in this paper we present a new algorithm for automatically learning hypernym (is-a) relations from text. Our method generalizes earlier work that had relied on using small numbers of handcrafted regular expression patterns to identify hypernym pairs.Using "dependency path" features extracted from parse trees, we introduce a general-purpose formalization and generalization of these patterns. Given a training set of text containing known hypernym pairs, our algorithm automatically extracts useful dependency paths and applies them to new corpora to identify novel pairs. On our evaluation task (determining whethertwo nouns in a news article participate in a hypernym relationship), our automatically extracted database of hypernyms attains both higher precision and higher recall than WordNet.
Stories of AAAI -- Before the Beginning and After: A Love Letter
This article provides a personal perspective, in three stories, on the origins of AAAI. In the first story, I explain the reasons justifying AAAI's existence. In the second story. In the second story, I recount some of the controvery over the name artificial intelligence, and explain why it was chosen as the new society's moniker. In the third story, I note that AI has not suffered from the applied versus research scism that has affected other societies. Finally, in the fourth story, I mention some of the early issues of finance.
Knowledge Is Power: A View from the Semantic Web
The emerging Semantic Web focuses on bringing knowledge representationlike capabilities to Web applications in a Web-friendly way. The ability to put knowledge on the Web, share it, and reuse it through standard Web mechanisms provides new and interesting challenges to artificial intelligence. In this paper, I explore the similarities and differences between the Semantic Web and traditional AI knowledge representation systems, and see if I can validate the analogy "The Semantic Web is to KR as the Web is to hypertext."
Reflections on the First AAAI Conference
What Do We Know about Knowledge? In this article, I will examine the first of these questions. AI has been slow to embrace this principle. Programs demonstrating research ideas in AI are often too large and not well enough documented to allow replication or sharing. What I would like to in diverse conditions. I wish to clarify the knowledge example, it was pretty clearly articulated in Biblical principle and try to increase our understanding times: "A man of knowledge increaseth of what programmers and program strength" (Proverbs 24: 5). Greek philosophers based their lives on acquiring The "knowledge is power" principle is most and transferring knowledge. In the course closely associated with Francis Bacon, from his of teaching, they sought to understand the 1597 tract on heresies: "Nam et ipsa scientia nature of knowledge and how we can establish potestas est." ("In and of itself, knowledge is knowledge of the natural world. B," along with quantification, "All A's are B's," Euclid's geometry firmly established the concept In the intervening several centuries before Plato, Socrates's pupil and Aristotle's mentor, was the first to pose the question in writing of the Middle Ages and the rise of modern science what we mean when we say that a person in the West, He was distinguishing empirical knowledge, church to make new knowledge fit with established lacking complete certainty, from the certain dogma.
Getting Back to "The Very Idea"
For many years, the very idea of artificial intelligence has been provocative and exciting. However, with a continually increasing focus on specialized subareas and somewhat narrow technical problems (both of which are inevitable and in many ways healthy), we may be torpedoing our core research agenda: the creation of a true synthetic intelligence. I reflect briefly on the essential interdependencies of the components of intelligence, the important roles of architecture and integration, and the need to get back to thinking about the very idea of AI. AAAI's role in the field has evolved over the years, but after a quarter-century as an organization, and a half-century as a field, it seems like AAAI is in an ideal situation to bring AI as a whole back to its roots. In 1985, the philosopher John Haugeland wrote a thoughtprovoking treatise on AI that he titled Artificial Intelligence: The Very Idea.
Whither AI: Identity Challenges of 1993-95
The 1993-95 period presented various "identity challenges" to the field of AI and to AAAI as a leading scientific society for the field. The euphoric days of the mid-1980s AI boom were over, various expectations of those times had not been met, and there was continuing concern about an AI "winter." The major challenge of these years was to chart a path for AI, designed and endorsed by the broadest spectrum of AI researchers, that built on past progress, explained AI's capacity for addressing fundamentally important intellectual problems and realistically predicted its potential to contribute to technological challenges of the coming decade. This reflection piece considers these challenges and the ways in which AAAI helped the field to move forward. Adolescence, the twenties, and the forties each bring particular "developmental" challenges to people, and, though surely coincidentally, elements of those life stages seem also to characterize the period of my presidency.
The Workshops at the Twentieth National Conference on Artificial Intelligence
Aliod, Diego Molla, Alonso, Eduardo, Bangalore, Srinivas, Beck, Joseph, Bhanu, Bir, Blythe, Jim, Boddy, Mark, Cesta, Amedeo, Grobelink, Marko, Hakkani-Tur, Dilek, Harabagiu, Sanda, Lege, Alain, McGuinness, Deborah L., Marsella, Stacy, Milic-Frayling, Natasha, Mladenic, Dunja, Oblinger, Dan, Rybski, Paul, Shvaiko, Pavel, Smith, Stephen, Srivastava, Biplav, Tejada, Sheila, Vilhjalmsson, Hannes, Thorisson, Kristinn, Tur, Gokhan, Vicedo, Jose Luis, Wache, Holger
The AAAI-05 workshops were held on Saturday and Sunday, July 9-10, in Pittsburgh, Pennsylvania. The thirteen workshops were Contexts and Ontologies: Theory, Practice and Applications, Educational Data Mining, Exploring Planning and Scheduling for Web Services, Grid and Autonomic Computing, Human Comprehensible Machine Learning, Inference for Textual Question Answering, Integrating Planning into Scheduling, Learning in Computer Vision, Link Analysis, Mobile Robot Workshop, Modular Construction of Humanlike Intelligence, Multiagent Learning, Question Answering in Restricted Domains, and Spoken Language Understanding.
A (Very) Brief History of Artificial Intelligence
In this brief history, the beginnings of artificial intelligence are traced to philosophy, fiction, and imagination. Early inventions in electronics, engineering, and many other disciplines have influenced AI. Some early milestones include work in problems solving which included basic work in learning, knowledge representation, and inference as well as demonstration programs in language understanding, translation, theorem proving, associative memory, and knowledge-based systems. The article ends with a brief examination of influential organizations and current issues facing the field.
Synthetic Adversaries for Urban Combat Training
Wray, Robert E., Laird, John E., Nuxoll, Andrew, Stokes, Devvan, Kerfoot, Alex
This article describes requirements for synthetic adversaries for urban combat training and a prototype application, MOUTBots. MOUTBots use a commercial computer game to define, implement, and test basic behavior representation requirements and the Soar architecture as the engine for knowledge representation and execution. The article describes how these components aided the development of the prototype and presents an initial evaluation against competence, taskability, fidelity, variability, transparency, and efficiency requirements.