Uncovering Constraint-Based Behavior in Neural Models via Targeted Fine-Tuning
Abstract
A growing body of literature has focused on detailing the linguistic knowledge embedded in large, pretrained language models. Existing work has shown that non-linguistic biases in models can drive model behavior away from linguistic generalizations. We hypothesized that competing linguistic processes within a language, rather than just non-linguistic model biases, could obscure underlying linguistic knowledge. We tested this claim by exploring a single phenomenon in four languages: English, Chinese, Spanish, and Italian. While human behavior has been found to be similar across languages, we find cross-linguistic variation in model behavior. We show that competing processes in a language act as constraints on model behavior and demonstrate that targeted fine-tuning can re-weight the learned constraints, uncovering otherwise dormant linguistic knowledge in models. Our results suggest that models need to learn both the linguistic constraints in a language and their relative ranking, with mismatches in either producing non-human-like behavior.
Cite
@article{arxiv.2106.01207,
title = {Uncovering Constraint-Based Behavior in Neural Models via Targeted Fine-Tuning},
author = {Forrest Davis and Marten van Schijndel},
journal= {arXiv preprint arXiv:2106.01207},
year = {2021}
}
Comments
Proceedings of 59th Annual Meeting of the Association for Computational Linguistics (ACL 2021)