Does It Capture STEL? A Modular, Similarity-based Linguistic Style Evaluation Framework

TL;DR

This paper introduces STEL, a modular framework for evaluating linguistic style in text, which controls for content and compares models based on style similarity across various dimensions.

Contribution

The paper presents STEL, a novel, flexible, and content-controlled style evaluation framework that enables comparison of different style measures and models.

Findings

BERT-based methods outperform traditional style measures

STEL effectively evaluates style across multiple dimensions

Framework encourages development of style-sensitive evaluation tools

Abstract

Style is an integral part of natural language. However, evaluation methods for style measures are rare, often task-specific and usually do not control for content. We propose the modular, fine-grained and content-controlled similarity-based STyle EvaLuation framework (STEL) to test the performance of any model that can compare two sentences on style. We illustrate STEL with two general dimensions of style (formal/informal and simple/complex) as well as two specific characteristics of style (contrac'tion and numb3r substitution). We find that BERT-based methods outperform simple versions of commonly used style measures like 3-grams, punctuation frequency and LIWC-based approaches. We invite the addition of further tasks and task instances to STEL and hope to facilitate the improvement of style-sensitive measures.