Solving and Explaining Analogy Questions Using Semantic Networks

Authors

  • Adrian Boteanu Worcester Polytechnic Institute
  • Sonia Chernova Worcester Polytechnic Institute

DOI:

https://doi.org/10.1609/aaai.v29i1.9400

Keywords:

semantic, semantic networks, analogy, interpretable, context

Abstract

Analogies are a fundamental human reasoning pattern that relies on relational similarity. Understanding how analogies are formed facilitates the transfer of knowledge between contexts. The approach presented in this work focuses on obtaining precise interpretations of analogies. We leverage noisy semantic networks to answer and explain a wide spectrum of analogy questions. The core of our contribution, the Semantic Similarity Engine, consists of methods for extracting and comparing graph-contexts that reveal the relational parallelism that analogies are based on, while mitigating uncertainty in the semantic network.We demonstrate these methods in two tasks: answering multiple choice analogy questions and generating human readable analogy explanations. We evaluate our approach on two datasets totaling 600 analogy questions. Our results show reliable performance and low false-positive rate in question answering; human evaluators agreed with 96% of our analogy explanations.

Downloads

Published

2015-02-18

How to Cite

Boteanu, A., & Chernova, S. (2015). Solving and Explaining Analogy Questions Using Semantic Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1). https://doi.org/10.1609/aaai.v29i1.9400

Issue

Section

AAAI Technical Track: Knowledge Representation and Reasoning