Thinking between the lines : computers and the comprehension of causal descriptions
著者
書誌事項
Thinking between the lines : computers and the comprehension of causal descriptions
（The MIT Press series in artificial intelligence）
MIT Press, c1994
大学図書館所蔵 件 / 全17件
-
該当する所蔵館はありません
- すべての絞り込み条件を解除する
注記
Based on the author thesis (doctoral)--MIT Artificial Intelligence Laboratory, 1992
Includes bibliographical references (p. [283]-293) and index
内容説明・目次
内容説明
Thinking Between the Lines targets a challenge at the heart of the artificial intelligence enterprise: the design of programs that can read and reason on the basis of written causal descriptions such as those that appear in encyclopedias, user manuals, and related sources. This capability of "thinking between the lines" -- codified in terms of a task called "causal reconstruction" -- bears directly on the larger question of how computers can usefully exploit the vast repertory of human knowledge concerning causal phenomena.Central to the approach presented is a cognitively inspired representation called "transition space," implemented in a program called PATHFINDER. The transition space representation embodies a conceptual shift from viewing the world primarily in terms of states -- or instantaneous snapshots of activity -- to viewing it primarily in terms of transitions -- ensembles of changes that can be articulated in language.
Transitions, according to this view, serve as antecedents and consequents of causality, and the space of all possible transitions -- or transition space -- serves as an arena for working out paths of association between the events mentioned within particular causal descriptions.Thinking between the Lines provides a computational framework and approach for realizing the significant opportunities that arise for intelligent, automated handling of technical material -- in routing information, answering questions, elaborating or summarizing information to meet the needs of particular individuals, and performing other useful tasks.Artificial Intelligence series
目次
- Introduction - what this book is about, the causal reconstruction task, the transition space representation, the PATHFINDER program, a note to the reader
- causal reconstruction - a closer look at the problem, task restrictions for PATHFINDER
- transition space - guidelines from perceptual psychology, representing transitions and events, using language to generate representations
- matching in transition space - overview, direct matches between referenced events, matches involving precedent events
- inference, background statements and assumptions - overview, employing inference, making use of background statements, identifying supporting assumptions
- exploratory transformations - overview, information-preserving transformations, non-information-preserving transformations
- making use of connecting statements - overview, temporal ordering statements, other specifications of association
- an extended example - phase 1 - parsing and encoding the input, phase 2 - applying exploratory transformations, phase 3 - associating the events, phase 4 - answering questions
- related literature - research in artificial intelligence, research in psychology, research in linguistics and philosophy
- conclusions - contributions of the research, extending the approach, new horizons. Appendices: PATHFINDER implementation
- PATHFINDER test examples.
「Nielsen BookData」 より