File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/relat/80/p80-1002_relat.xml
Size: 2,163 bytes
Last Modified: 2025-10-06 14:15:59
<?xml version="1.0" standalone="yes"?> <Paper uid="P80-1002"> <Title>UNDERSTANDING SCENE DESCRIPTIONS AS EVg~NT SIMULATIONS I</Title> <Section position="9" start_page="10" end_page="10" type="relat"> <SectionTitle> 5.~ RELATED WORK </SectionTitle> <Paragraph position="0"> A number of papers related the the topics treated here have appeared in recent years. Many are listed in \[8\] which also provides some ideas on the generation of scene descriptions. This work has been pervasively influenced by the ideas of Bill Woods on &quot;procedural semantics&quot;, especially as presented in \[9\].</Paragraph> <Paragraph position="1"> Representations for large-scale space (paths, maps, etc.) were treated in Kuipers' thesis \[I0\]. Novak \[11\] wrote a program that generated and used diagrams for understanding physics problems. Simmons \[12\] wrote programs that understood simple scene descriptions involving several known objects. Inferences about the causes and effects of actions and events have been considered by Schank and Abelson\[13\] and Rieger\[14\].</Paragraph> <Paragraph position="2"> Johnson-Laird\[15\] has investigated problems in understanding scenes with spatial locative prepositions, as has Herskovits\[16\]. Recent work by Forbus\[17\] has developed a very interesting paradigm for qualitative reasoning in physics, built on work by deKleer\[18,19\], and related to work by Hayes\[20,21\]. My comments on pronoun resolution are in the same spirit as Hobbs\[22\], although Hobbs's &quot;predicate interpretation&quot; is quite different from my &quot;analog spatial models&quot;. Ideas on the adaptation of prototypes for the representation of 3-D shape were explored in Waltz \[23\]. A effort toward qualitative mechanics is described in Bundy \[24\]. Also relevant is the work on mental imagery of Kosslyn & Shwartz\[25\] and Hinton\[26\].</Paragraph> <Paragraph position="3"> I would like to acknowledge especially the helpful comments of Ken Forbus, and also the help I have received from Bill Woods, Candy Sidner, Jeff Gibbons, Rusty Bobrow, David Israel, and Brad Goodman.</Paragraph> </Section> class="xml-element"></Paper>