Composition and Deformance: Measuring Imageability with a Text-to-Image Model

TL;DR

This paper introduces a computational approach using text-to-image models to measure the imageability of words and texts, examining how compositional changes affect imageability detection.

Contribution

It proposes novel methods leveraging text-to-image generation to quantify imageability and analyze compositional effects, bridging psycholinguistic concepts with AI models.

Findings

High correlation between computational and human imageability judgments.

Proposed measures respond more consistently to compositional changes than baselines.

Model detects imageability changes caused by text deformation.

Abstract

Although psycholinguists and psychologists have long studied the tendency of linguistic strings to evoke mental images in hearers or readers, most computational studies have applied this concept of imageability only to isolated words. Using recent developments in text-to-image generation models, such as DALLE mini, we propose computational methods that use generated images to measure the imageability of both single English words and connected text. We sample text prompts for image generation from three corpora: human-generated image captions, news article sentences, and poem lines. We subject these prompts to different deformances to examine the model's ability to detect changes in imageability caused by compositional change. We find high correlation between the proposed computational measures of imageability and human judgments of individual words. We also find the proposed measures more consistently respond to changes in compositionality than baseline approaches. We discuss possible effects of model training and implications for the study of compositionality in text-to-image models.