---
title: "A Probabilistic Approach to Marker Propagation"
authors:
  - "Dekai Wu"
doi: ""
url: "https://ijcai.org/proceedings/1989/92"
pdf: "https://ijcai.org/proceedings/1989/0092.pdf"
venue: "Proceedings of the Eleventh International Joint Conference on Artificial Intelligence"
year: 1989
pages: "574-581"
track: "Cognitive Models"
keywords:
---

# A Probabilistic Approach to Marker Propagation

Dekai Wu

*Proceedings of the Eleventh International Joint Conference on Artificial Intelligence*, pages 574-581.

## Abstract

Pot entially, the advantages of marker-passing over local connectionist techniques for associative inference are (1) the ability to differentiate variable bindings, and (2) reduction in th e search space and/ or number of processing ele ments. However, the latter advantage has mostly been realized at the expense of accuracy and pr edictability. In this paper we consider a class of associative inference to which marker passing is often applied, variously called abductive inference, schema selection, or pattern completion. Analysis of marker semantics in a standard semantic net representation leads to a proposal for more strictly regulated marker propagation. An implementation strategy employing an augmented relaxation network is outlined.