{"type":"ScholarlyArticle","title":"Using Device Models to Facilitate the Retrieval of Multimedia Design Information","authors":[{"name":"Catherine Baudin","slug":"catherine-baudin","given":"Catherine","family":"Baudin","affiliation":""},{"name":"Jody Gevins Underwood","slug":"jody-gevins-underwood","given":"Jody Gevins","family":"Underwood","affiliation":""},{"name":"Vinod Baya","slug":"vinod-baya","given":"Vinod","family":"Baya","affiliation":""}],"abstract":"An engineering team generates information in the form of meeting summaries, progress reports, engineering notes, spreadsheet calculations and CAD drawings. While complete \"machine intelligible\" models of an artifact design are still difficult to acquire, canned text information or videotapes of meetings are easy to capture but difficult to reuse. Dedal is an interface that facilitates the reuse of design experience by providing an intelligent guide for retrieving text, graphics and videotaped documents. It uses : (1) concepts from a model of the designed artifact to index and query design documents, and (2) a set of heuristics that reason from the model to \"guess\" where the answers to a question may be documented when the retrieval fails. We observed an engineer asking questions to Dedal to access records of a shock absorber design and found that (1) using a model to index the records significantly increased the precision and recall of the information retrieved when compared with a baseline retrieval system, and (2.) the heuristics contributed to this performance by increasing the recall of Dedal by 40%.","doi":null,"url":"https://ijcai.org/proceedings/1993/171","pdf":"https://ijcai.org/proceedings/1993/0171.pdf","markdown":"https://ijcai.org/proceedings/1993/171.md","bibtex":"https://ijcai.org/proceedings/1993/bibtex/171","volume":{"slug":"1993","title":"Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1993","url":"https://ijcai.org/proceedings/1993/","year":1993,"location":"Chambéry, France","dates":"","editors":"Ruzena Bajcsy","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Natural Language","track":"Natural Language","number":171,"pages":{"first":1237,"last":1244},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}