conceptual dependency
In plain wordsA 1970s theory for representing the meaning of sentences with a small set of basic actions, so that 'John gave Mary a book' and 'Mary got a book from John' come out the same.
A theory and notation for representing the meaning of natural-language sentences independently of their wording or language, by decomposing events into a small set of primitive acts — such as ATRANS (transfer of possession), PTRANS (change of location), MTRANS (transfer of information), PROPEL, INGEST and EXPEL — connected to actors, objects, recipients, instruments and causal links between states and events. Paraphrases receive identical representations, and inferences attach to the primitives: any ATRANS implies that the recipient now has the object. Conceptual dependency underpinned 1970s language-understanding programs at Stanford and Yale such as MARGIE, SAM and PAM and the higher-level structures of scriptsscript, n.: In classic AI, a stored outline of a familiar sequence of events, such as eating at a restaurant, that helps a program understand a story by filling in what normally happens., plans and goals. Critics argued that no fixed set of primitives can capture all meaning; its ideas resurface in semantic parsingsemantic parsing, n.: Translating a sentence into a precise, machine-executable form — such as a database query or a logical formula — so that a computer can act on what was asked. and event-based knowledge representationsknowledge representation, n.: The study of how to record knowledge about objects, categories, rules and events in a precise format, so that a program can reason with it and reach conclusions nobody typed in..
Origin
Introduced by Roger Schank in his 1969 University of Texas doctoral thesis, 'A Conceptual Dependency Representation for a Computer-Oriented Semantics', developed at Stanford and set out in full in a 1972 paper in Cognitive Psychology. The Stanford MARGIE system (reported at IJCAI 1973, described in the 1975 book Conceptual Information Processing) used it for parsing, inference and paraphrase generation; Schank continued the work at Yale from 1974.
Related
- scriptscript, n.: In classic AI, a stored outline of a familiar sequence of events, such as eating at a restaurant, that helps a program understand a story by filling in what normally happens.
- frameframe, n.: In classic AI, a ready-made template for a familiar kind of thing or event, such as a kitchen or a job interview, with blanks to fill in and sensible default values.
- semantic networksemantic network, n.: A way of storing knowledge as a web of concepts joined by labeled arrows, such as 'canary — is a — bird' and 'bird — can — fly', so a program can follow the links.
- knowledge representationknowledge representation, n.: The study of how to record knowledge about objects, categories, rules and events in a precise format, so that a program can reason with it and reach conclusions nobody typed in.
- semantic parsingsemantic parsing, n.: Translating a sentence into a precise, machine-executable form — such as a database query or a logical formula — so that a computer can act on what was asked.
- commonsense reasoningcommonsense reasoning, n.: The everyday background knowledge and reasoning people take for granted — dropped glasses break, hungry people eat, nobody is in two places at once — which machines long struggled to match.
Sources
- Schank, R. C. (1972). Conceptual Dependency: A Theory of Natural Language Understanding. Cognitive Psychology 3(4), 552–631.