Paper: Retrieving Word Associations with a Simple Neighborhood Algorithm in a Graph-based Resource

ACL ID W14-4708
Title Retrieving Word Associations with a Simple Neighborhood Algorithm in a Graph-based Resource
Venue Workshop on Cognitive Aspects of the Lexicon
Session
Year 2014
Authors

The paper explains the procedure to obtain word associations starting from a graph that has not been specifically built for that purpose. Our goal is being able to simulate human word asso- ciations by using the simplest possible methods, including the basic tools of a co-occurrence network from a non-annotated corpus, and a very simple search algorithm based on neighbor- hood. The method has been tested in the Cogalex shared task, revealing the difficulty of achieving word associations without semantic annotation.