Comparing Styles across Languages: A Cross-Cultural Exploration of Politeness
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 33 of its 57 references that are in the map. First posted on arXiv 11 Oct 2023.
Builds on
33 of 57 references.
References · 33
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2016Enriching Word Vectors with Subword Informationcited by 1,578
- 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
- 2019How multilingual is Multilingual BERT?cited by 642
- 2020Revisiting Pre-Trained Models for Chinese Natural Language Processingcited by 262
- 2022Challenges and Strategies in Cross-Cultural NLPcited by 216
- 2013A Computational Approach to Politeness with Application to Social Factorscited by 104
21 more
- 2020On the Language Neutrality of Pre-trained Multilingual Representationscited by 82
- 2021First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERTcited by 64
- 2018Polite Dialogue Generation Without Parallel Datacited by 57
- 2023Multilingual Language Models are not Multicultural: A Case Study in Emotioncited by 54
- 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 51
- 2020XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detectioncited by 31
- 2022BERTIN: Efficient Pre-Training of a Spanish Language Model using Perplexity Samplingcited by 30
- 2018Multi-Task Neural Models for Translating Between Styles Within and Across Languagescited by 28
- 2021Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexicacited by 23
- 2022TyDiP: A Dataset for Politeness Classification in Nine Typologically Diverse Languagescited by 21
- 2021Few-shot Controllable Style Transfer for Low-Resource Multilingual Settingscited by 20
- 2022Empathic Conversations: A Multi-level Dataset of Contextualized Conversationscited by 20
- 2022Controlling Translation Formality Using Pre-trained Multilingual Language Modelscited by 14
- 2022MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languagescited by 13
- 2016Interpreting Neural Networks to Improve Politeness Comprehensioncited by 12
- 2020Studying Politeness across Cultures Using English Twitter and Mandarin Weibocited by 9
- 2020Facilitating the Communication of Politeness through Fine-Grained Paraphrasingcited by 9
- 2021Towards Universality in Multilingual Text Rewritingcited by 7
- 2022StyLEx: Explaining Style Using Human Lexical Annotationscited by 3
- 2023TopEx: Topic-based Explanations for Model Comparisoncited by 3
- 2023In What Languages are Generative Language Models the Most Formal? Analyzing Formality Distribution across Languagescited by 2
Built on by
Citing papers per year: 2024: 2.
2 papers.