A Cognitive Regularizer for Language Modeling
This work addresses the challenge of enhancing language model performance and interpretability for NLP researchers, though it is incremental as it builds on existing UID theory and regularization techniques.
The authors tackled the problem of improving statistical language models by incorporating the uniform information density (UID) hypothesis as an inductive bias, resulting in consistent perplexity improvements across ten languages, especially with limited training data, and generating more lexically diverse text.
The uniform information density (UID) hypothesis, which posits that speakers behaving optimally tend to distribute information uniformly across a linguistic signal, has gained traction in psycholinguistics as an explanation for certain syntactic, morphological, and prosodic choices. In this work, we explore whether the UID hypothesis can be operationalized as an inductive bias for statistical language modeling. Specifically, we augment the canonical MLE objective for training language models with a regularizer that encodes UID. In experiments on ten languages spanning five language families, we find that using UID regularization consistently improves perplexity in language models, having a larger effect when training data is limited. Moreover, via an analysis of generated sequences, we find that UID-regularized language models have other desirable properties, e.g., they generate text that is more lexically diverse. Our results not only suggest that UID is a reasonable inductive bias for language modeling, but also provide an alternative validation of the UID hypothesis using modern-day NLP tools.