Learning Relations by Pathfinding

By Bradley L. Richards, Raymond J. Mooney. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Learning to construct knowledge bases from the World Wide Web (2000, methodology): “Our algorithm for constructing the path part of a clause is a variant of Richards and Mooney’s relational pathfinding method [55].”
A Shortest Path Dependency Kernel for Relation Extraction (2005, background): “Our shortest-path intuition bears some similarity with the underlying assumption of the relational pathfinding algorithm from (Richards and Mooney, 1992) : “in most relational domains, important concepts will be represented by a small number of fixed paths among the constants defining a positive ins”
Mapping and Revising Markov Logic Networks for Transfer Learning (2007, background): “Relational pathfinding (RPF) is a data-driven approach to rule discovery designed to overcome plateaus and local maxima ( Richards & Mooney 1992 ).”
Hinge-Loss Markov Random Fields and Probabilistic Soft Logic (2015, unknown): “Based on rule-learning techniques from inductive logic programming (e.g., Richards and Mooney, 1992; De Raedt and Dehaspe, 1996) a series of approaches have sought to learn MLN rules from relational data.”
Random Walk Inference and Learning in A Large Scale Knowledge Base (2011, methodology): “It has been embodied previously in first-order learning systems (Richards and Mooney, 1992) as well as N-FOIL, and relational database searching systems (Bhalotia et al.”
Statistical Relational Artificial Intelligence: Logic, Probability, and Computation (2016, methodology): “ey used relational path finding [Richards and Mooney, 1992] for learning MLNs by lifting these hypergraphs.”