Matches in SemOpenAlex for { <https://semopenalex.org/work/W130986543> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W130986543 abstract "Natural language generation can be divided into two stages: deep generation, in which content and style are specified, and realization, in which this specification is converted into text. This thesis rejects the goal-driven planning of previous work, using instead the salience of objects in a database to provide data-driven selection--a computationally much less expensive approach.This research studies the generation of descriptions of natural suburban scenes. The phenomenon of salience was explored through a series of psychological experiments--in some, subjects provided subjective ratings of the relative importance of the items in photographs; in others, subjects wrote short descriptions of the same pictures. The rating data provided the basis for the beginnings of a theory of visual salience as a perceptual phenomenon, while analysis of the combination of rating and textual data showed how salience orders the mention of objects in descriptions.The LISP program GENARO plans paragraph descriptions of scenes. Its input representation, though hand-built, is designed to simulate the perceptual output of a computer vision system, and includes an annotation of empirically-based salience values. GENARO uses rules (each of which knows about some specific or stylistic effect) to build rhetorical specifications (which are then realized by McDonald's MUMBLE program). Its processing is data-driven, i.e. a current-item is selected from a salience-ordered list of perceptual objects, and it and its salience are the primary determiners for the actions of the rules. This planning process is myopic--it has no explicit goal. Also, all of GENARO's actions are indelible--the control structure provides no look-ahead or backup.The fact that this localized planning is able to devise quite natural-sounding paragraphs demonstrates that a data-driven approach to deep generation is viable, and that salience can be a powerful heuristic in guiding natural language generation." @default.
- W130986543 created "2016-06-24" @default.
- W130986543 creator A5081034612 @default.
- W130986543 date "1983-01-01" @default.
- W130986543 modified "2023-09-23" @default.
- W130986543 title "Data-driven indelible planning of discourse generation using salience" @default.
- W130986543 hasPublicationYear "1983" @default.
- W130986543 type Work @default.
- W130986543 sameAs 130986543 @default.
- W130986543 citedByCount "6" @default.
- W130986543 crossrefType "journal-article" @default.
- W130986543 hasAuthorship W130986543A5081034612 @default.
- W130986543 hasConcept C108154423 @default.
- W130986543 hasConcept C111472728 @default.
- W130986543 hasConcept C138885662 @default.
- W130986543 hasConcept C154945302 @default.
- W130986543 hasConcept C15744967 @default.
- W130986543 hasConcept C169760540 @default.
- W130986543 hasConcept C180747234 @default.
- W130986543 hasConcept C192562157 @default.
- W130986543 hasConcept C204321447 @default.
- W130986543 hasConcept C26760741 @default.
- W130986543 hasConcept C41008148 @default.
- W130986543 hasConcept C41895202 @default.
- W130986543 hasConcept C50335755 @default.
- W130986543 hasConceptScore W130986543C108154423 @default.
- W130986543 hasConceptScore W130986543C111472728 @default.
- W130986543 hasConceptScore W130986543C138885662 @default.
- W130986543 hasConceptScore W130986543C154945302 @default.
- W130986543 hasConceptScore W130986543C15744967 @default.
- W130986543 hasConceptScore W130986543C169760540 @default.
- W130986543 hasConceptScore W130986543C180747234 @default.
- W130986543 hasConceptScore W130986543C192562157 @default.
- W130986543 hasConceptScore W130986543C204321447 @default.
- W130986543 hasConceptScore W130986543C26760741 @default.
- W130986543 hasConceptScore W130986543C41008148 @default.
- W130986543 hasConceptScore W130986543C41895202 @default.
- W130986543 hasConceptScore W130986543C50335755 @default.
- W130986543 hasLocation W1309865431 @default.
- W130986543 hasOpenAccess W130986543 @default.
- W130986543 hasPrimaryLocation W1309865431 @default.
- W130986543 hasRelatedWork W1499050190 @default.
- W130986543 hasRelatedWork W1566718427 @default.
- W130986543 hasRelatedWork W157197848 @default.
- W130986543 hasRelatedWork W1589174919 @default.
- W130986543 hasRelatedWork W1992258378 @default.
- W130986543 hasRelatedWork W2002056789 @default.
- W130986543 hasRelatedWork W2081256485 @default.
- W130986543 hasRelatedWork W2082821553 @default.
- W130986543 hasRelatedWork W2116678423 @default.
- W130986543 hasRelatedWork W2251395535 @default.
- W130986543 hasRelatedWork W2396156702 @default.
- W130986543 hasRelatedWork W2403975755 @default.
- W130986543 hasRelatedWork W2561858436 @default.
- W130986543 hasRelatedWork W27299142 @default.
- W130986543 hasRelatedWork W2951011353 @default.
- W130986543 hasRelatedWork W30026100 @default.
- W130986543 hasRelatedWork W3083290108 @default.
- W130986543 hasRelatedWork W3200893854 @default.
- W130986543 hasRelatedWork W68258046 @default.
- W130986543 hasRelatedWork W2184392230 @default.
- W130986543 isParatext "false" @default.
- W130986543 isRetracted "false" @default.
- W130986543 magId "130986543" @default.
- W130986543 workType "article" @default.