An Association Network for Computing Semantic Relatedness

Authors

  • Keyang Zhang Shanghai Jiao Tong University
  • Kenny Zhu Shanghai Jiao Tong University
  • Seung-won Hwang POSTECH

DOI:

https://doi.org/10.1609/aaai.v29i1.9220

Keywords:

Concept Association, Cognitive computing, Semantic Similarity

Abstract

To judge how much a pair of words (or texts) are semantically related is acognitive process. However, previous algorithms for computing semanticrelatedness are largely based on co-occurrences within textualwindows, and do not actively leverage cognitive human perceptions ofrelatedness. To bridge this perceptional gap, we propose to utilizefree association as signals to capture such human perceptions.However, free association, being manually evaluated,has limited lexical coverage and is inherently sparse. We propose to expand lexical coverage and overcome sparseness by constructing an association network of terms and concepts that combines signals from free association norms and five types of co-occurrences extracted from therich structures of Wikipedia. Our evaluation results validate thatsimple algorithms on this network give competitive results incomputing semantic relatedness between words and between shorttexts.

Downloads

Published

2015-02-10

How to Cite

Zhang, K., Zhu, K., & Hwang, S.- won. (2015). An Association Network for Computing Semantic Relatedness. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1). https://doi.org/10.1609/aaai.v29i1.9220

Issue

Section

AAAI Technical Track: Cognitive Systems