Comparing Styles across Languages: A Cross-Cultural Exploration of Politeness

TL;DR

This paper presents a framework for analyzing and comparing stylistic differences, specifically politeness, across multiple languages using multilingual language models, resulting in a new multilingual politeness dataset.

Contribution

It introduces a novel explanation framework that extracts stylistic lexica and compares politeness styles across four languages, providing interpretable cross-cultural insights.

Findings

Created the first holistic multilingual politeness dataset

Demonstrated the framework's effectiveness in capturing stylistic differences

Provided insights into cultural variations in politeness expressions

Abstract

Understanding how styles differ across languages is advantageous for training both humans and computers to generate culturally appropriate text. We introduce an explanation framework to extract stylistic differences from multilingual LMs and compare styles across languages. Our framework (1) generates comprehensive style lexica in any language and (2) consolidates feature importances from LMs into comparable lexical categories. We apply this framework to compare politeness, creating the first holistic multilingual politeness dataset and exploring how politeness varies across four languages. Our approach enables an effective evaluation of how distinct linguistic categories contribute to stylistic variations and provides interpretable insights into how people communicate differently around the world.