Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art
Chen Cecilia Liu, Iryna Gurevych, Anna Korhonen
TL;DR
The paper addresses the lack of a shared understanding of culture in NLP by proposing a fine-grained, anthropology-grounded taxonomy that organizes cultural variation into ideational, linguistic, and social elements. It surveys 127 publications from leading NLP venues, categorizing resources and methods according to the taxonomy to map progress and identify gaps. Key contributions include the taxonomy itself, a systematic survey of resources and modeling approaches, and practical recommendations for data collection, model adaptation, and evaluation that account for cultural diversity. The study highlights notable progress in knowledge and values resources while revealing gaps in multilingual coverage, social-contextual annotations, and deeper cultural modeling beyond surface adaptations, with implications for fairer and more inclusive NLP systems. This taxonomy and survey provide a framework for guiding future research and resource development toward culturally aware NLP with broader real-world impact.
Abstract
The surge of interest in "culture" in NLP has inspired much recent research, but a shared understanding of "culture" remains unclear, making it difficult to evaluate progress in this emerging area. Drawing on prior research in NLP and related fields, we propose a fine-grained taxonomy of elements in culture that can provide a systematic framework for analyzing and understanding research progress. Using the taxonomy, we survey existing resources and methods for culturally aware and adapted NLP, providing an overview of the state of the art and the research gaps that still need to be filled.
