A Comprehensive Comparison of Neural Networks as Cognitive Models of Inflection

Neural networks have long been at the center of a debate around the cognitive mechanism by which humans process inflectional morphology. This debate has gravitated into NLP by way of the question: Are neural networks a feasible account for human behavior in morphological inflection? We address that...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-10
Main Authors: Wiemerslage, Adam, Dudy, Shiran, Kann, Katharina
Format: Article
Language:English
Subjects:
Cognitive tasks
Human behavior
Morphology
Neural networks
Questions
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural networks have long been at the center of a debate around the cognitive mechanism by which humans process inflectional morphology. This debate has gravitated into NLP by way of the question: Are neural networks a feasible account for human behavior in morphological inflection? We address that question by measuring the correlation between human judgments and neural network probabilities for unknown word inflections. We test a larger range of architectures than previously studied on two important tasks for the cognitive processing debate: English past tense, and German number inflection. We find evidence that the Transformer may be a better account of human behavior than LSTMs on these datasets, and that LSTM features known to increase inflection accuracy do not always result in more human-like behavior.
ISSN:2331-8422