AI Research Atlas
Thesis / research report

Semantic memory

SIR stores facts and reasons over them

A small language system built an internal model from statements and searched it to answer later questions.

Bertram Raphael

AI topics

Explore related entries. Larger tags appear on more entries.

The contribution

SIR accepted restricted English statements and questions. It stored relational information using associations and property lists, then searched that model to answer queries and draw deductions. The separation between receiving a fact and later retrieving its consequences makes it an early example of memory supporting an ongoing interaction.

What this does not establish

Its language and reasoning were constrained by the supplied formats and domain. Storing conversational facts did not establish broad language understanding or unlimited learning.

Why this date?

The linked MIT archive dates AI-TR-220 to June 1964. SHRDLU cites this work using a 1964 label but points to its later chapter in Semantic Information Processing; the entry anchors the original report.

This entry follows the linked publication. Read the source and date conventions.

Comments

Discuss this research, ask a question, or suggest a correction. Comments appear after the site owner approves them.

Loading comments…

Sign in with ChatGPT to comment

Use your OpenAI account. Published comments show the display name you choose, not your account email.