ERIC Number: ED161024
Record Type: RIE
Publication Date: 1975-Aug
Reference Count: 0
Sam--A Story Understander. Research Report No. 43.
Schank, Roger C.; And Others
SAM (Script Applier Mechanism), a computer program designed to understand stories that rely heavily on scripts (typical sequences of events in particular contexts), is described in this report. Chapter one, which discusses SAM's background, shows how causal chaining was developed to connect events in stories, presents a typical script, and explains the general form for a script. The following chapter presents examples to show how SAM processes stories by creating a linked causal chain of conceptualizations that represent what took place and then generating the output back in English. Chapter three describes the following components of SAM: the English-to-conceptual dependency analyzer; the EXEC (executive program), which decides which script is required for each input; the script applier, which constructs a story representation from conceptual dependency input; the generator, which produces an English sentence as an output; and the Chinese generator, which can translate the output into Chinese. The chapter also explains how SAM creates paraphrases and summaries of processed stories and how it answers four types of questions that rely on information in a script. A brief concluding chapter notes that SAM's significance lies in its provision of a test for a theory of understanding based on scripts. (GW)
Publication Type: Reports - Research
Education Level: N/A
Sponsor: Advanced Research Projects Agency (DOD), Washington, DC.; Office of Naval Research, Arlington, VA.
Authoring Institution: Yale Univ., New Haven, CT. Dept. of Computer Science.