Natural Language Processing has seen impressive gains in recent years. This research includes the demonstration by NLP models to have turned into useful technologies with improved capabilities, measured in terms of how well they match human behavior captured in web-scale language data or through annotations. However, human behavior is inherently shaped by the cultural contexts humans are embedded in, the values and beliefs they hold, and the social practices they follow, part of which will be reflected in the data used to train NLP models, and the behavior these NLP models exhibit. Not accounting for this factor could cause incongruencies and misalignments between the cultural contexts that underpin the NLP model development process and the multi-cultural ecosystems they are expected to operate in. These misalignments may result in various harms, including barriers to those from under-represented cultures, violating cultural norms and values, and erasure of cultural knowledge.

While recent work in the field has started to acknowledge this issue, it is important to build a long-term research agenda for the NLP community around (1) deeper understanding of how global cultures and NLP technologies intersect, in a way that goes beyond multi-lingual and cross-lingual research, (2) how to detect, measure, and attempt to mitigate potential biases and harms in NLP technology in ways that reflect local cultures and values, and (3) how to build more cross-culturally competent NLP systems. This agenda requires looking beyond the NLP community, bringing in multi-disciplinary expertise to shape the inquiries in this important area.

We propose this workshop as a way to bring together the growing number of NLP researchers interested in this topic, along with a community of scholars with multi-disciplinary expertise spanning linguistics, social sciences, and cultural anthropology. Our aim is to build this important inquiry within NLP on a solid basis of cultural theories from social sciences. To this end, the workshop program will focus on the following themes: Inclusivity and Representation of cultures in NLP, Cultural harms of NLP technologies, and Culture Sensitive lens on Social Biases and Harms in NLP. We invite papers on topics including the following (but not limited to):

• How does culture shape NLP data, annotations, models, and applications?
• How can we use methods from social sciences to study the cultural impacts of NLP?
• How to incorporate cultural knowledge in NLP data and models in recurrent/dynamic ways?
• How can we detect and mitigate cultural harms of NLP technology?
• How does NLP technology reflect and/or reinforce cultural values and stereotypes?
• How can we develop NLP technology in a way that is representative of global cultures?
• How can we effectively involve annotators from across cultural contexts in NLP research?
• How can NLP data collection methods be improved to better capture cultural differences?
• What are the perceptions of NLP tasks of crowd workers from different cultures?
• How can NLP technology impact the way we think about language and culture?
• How to build bridges between NLP researchers, linguists, and language communities?
• How can multi-modal models accurately capture, represent and enhance cultural expressions?
• What can we learn from low-resource cultures that could improve NLP technologies?

Requirements for Direct Submission: Both short papers and long papers are welcome, and must follow all of the ACL paper submission requirements.

Submission Link: TBD.