Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance
Additional information
Authors
Petersen M.,
van der Plas L.
Type
Article in conference proceedings
Year
2023
Language
English
Abstract
"While analogies are a common way to evaluate word embeddings in NLP, it is also of interest to investigate whether or not analogical reasoning is a task in itself that can be learned. In this paper, we test several ways to learn basic analogical reasoning, specifically focusing on analogies that are more typical of what is used to evaluate analogical reasoning in humans than those in commonly used NLP benchmarks. Our experiments find that models are able to learn analogical reasoning, even with a small amount of data. We additionally compare our models to a dataset with a human baseline, and find that after training models approach human performance.
Conference proceedings
"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing"
Numero ( Mese )
December
Publisher
"Association for Computational Linguistics"
Meeting name
EMNLP
Meeting place
"Singapore"
Meeting date
December 2023
Pages (or article number)
"16414-16425"
