Awesome Cultural NLP: ![Awesome](https://camo.githubusercontent.com/8693bde04030b1670d5097703441005eba34240c32d1df1eb82a5f0d6716518e/68747470733a2f2f63646e2e7261776769742e636f6d2f73696e647265736f726875732f617765736f6d652f643733303566333864323966656437386661383536353265336136336531353464643865383832392f6d656469612f62616467652e737667)
A curated list of awesome cultural NLP resources, inspired by awesome-computer-vision.
Table Of Contents
Title |
Conference / Journal |
Paper |
Code |
Remarks |
Towards Measuring and Modeling “Culture” in LLMs: A Survey |
Arxiv 2024 |
2403.15412 |
Github |
Cool paper! |
Challenges and Strategies in Cross-Cultural NLP |
ACL 2022 |
2203.10020 |
|
|
|
|
|
|
|
Title |
Conference / Journal |
Paper |
Code |
Remarks |
CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies |
Arxiv 2024 |
2404.15238 |
|
|
NORMAD: A Benchmark for Measuring the Cultural Adaptability of Large Language Models |
Arxiv 2024 |
2404.12464 |
|
|
An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance |
Arxiv 2024 |
2404.01247 |
Code and Data |
Data + Application |
Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys |
EACL Findings 2024 |
2401.10352 |
Dataset |
|
Culturally Aware Natural Language Inference |
EMNLP 2023 (Findings) |
2023.findings-emnlp.509 |
Data |
|
Global Voices, Local Biases: Socio-Cultural Prejudices across Languages |
EMNLP 2023 |
2310.17586 |
Data |
Data+Analysis |
NORMSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly |
EMNLP 2023 |
2210.08604 |
Code and Data |
NormsKB |
GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition |
Neurips 2023 |
2301.02560 |
Code and Data |
|
SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models |
ACL 2023 |
2305.11840 |
Code |
|
FORK: A Bite-Sized Test Set for Probing Culinary Cultural Biases in Commonsense Reasoning Models |
ACL Findings 2023 |
2023.findings-acl.631 |
Dataset |
|
Multi-lingual and Multi-cultural Figurative Language Understanding |
ACL Findings 2023 |
2305.16171 |
Code |
|
EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English |
ACL Findings 2022 |
2203.14498 |
|
|
Re-contextualizing Fairness in NLP: The Case of India |
AACL 2022 |
2209.12226 |
Data |
Data+Analysis |
Visually Grounded Reasoning across Languages and Cultures |
EMNLP 2021 |
2109.13238 |
Website |
EMNLP 2021 Best Paper |
Would you Rather? A New Benchmark for Learning Machine Alignment with Cultural Values and Social Preferences |
ACL 2020 |
2020.acl-main.477/ |
|
|
|
|
|
|
|
Title |
Conference / Journal |
Paper |
Code |
Remarks |
CIC: A framework for Culturally-aware Image Captioning |
IJCAI 2024 |
2402.05374 |
Webpage |
|
|
|
|
|
|
Title |
Conference / Journal |
Paper |
Code |
Remarks |
GIVL: Improving Geographical Inclusivity of Vision-Language Models With Pre-Training Methods |
CVPR 2023 |
2301.01893 |
Code (not released yet) |
|
|
|
|
|
|
Title |
Conference / Journal |
Paper |
Code |
Remarks |
On the Cultural Gap in Text-to-Image Generation |
Arxiv 2023 |
2307.02971 |
Code |
|
|
|
|
|
|
Title |
Conference / Journal |
Paper |
Code |
Remarks |
ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation |
ACL 2024 |
2401.06310 |
|
|
DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity |
ICLR 2024 |
2308.06198 |
Code |
|
Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models |
arxiv 2023 |
2310.01929 |
Code (not released yet) |
|
Inspecting the Geographical Representativeness of Images from Text-to-Image Models |
ICCV 2023 |
2305.11080 |
|
|
Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale |
FAccT '23 |
2211.03759 |
|
|
Multilingual Conceptual Coverage in Text-to-Image Models |
ACL 2023 |
2306.01735 |
Code |
|
|
|
|
|
|
Title |
Conference / Journal |
Paper |
Code |
Remarks |
CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting |
arxiv 2024 |
2404.10199v1 |
Code |
|
Knowledge of cultural moral norms in large language models |
ACL 2023 |
2306.01857 |
|
|
Multilingual Language Models are not Multicultural: A Case Study in Emotion |
WASSA: ACL 2023 |
2307.01370 |
|
|
Social Commonsense for Explanation and Cultural Bias Discovery |
|
|
|
|
|
|
|
|
|
Title |
Conference / Journal |
Paper |
Code |
Remarks |
Exploring Visual Culture Awareness in GPT-4V: A Comprehensive Probing |
arxiv 2024 |
2402.06015 |
|
|
‘Person’ == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion |
EMNLP 2023 Findings |
2310.19981 |
|
|
|
|
|
|
|
Cross-cultural Variations
Title |
Conference / Journal |
Paper |
Code |
Remarks |
Cross-Cultural Analysis of Human Values, Morals, and Biases in Folk Tales |
EMNLP 2023 |
2023.emnlp-main.311 |
|
|
Social Commonsense for Explanation and Cultural Bias Discovery |
EACL 2023 |
2023.eacl-main.271.pdf |
|
|
Cross-cultural variation of speech-accompanying gesture: A review |
Language and Cognitive Processes: Volume 24, Issue 2, 2009 |
10.1080/01690960802586188 |
|
|
|
|
|
|
|
Title |
Conference / Journal |
Paper |
Code |
Remarks |
Unintended Impacts of LLM Alignment on Global Representation |
arxiv 2024 |
2402.15018 |
|
|
Probing Pre-Trained Language Models for Cross-Cultural Differences in Values |
C3NLP: EACL 2023 |
2203.13722 |
|
Analysis |
Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study |
C3NLP: EACL 2023 |
2303.17466 |
|
Analysis |
|
|
|
|
|
Title |
Conference / Journal |
Paper |
Code |
Remarks |
Cultural Concept Adaptation on Multimodal Reasoning |
EMNLP 2023 |
EMNLP Main 18 |
|
|
|
|
|
|
|
Title |
Conference / Journal |
Paper |
Code |
Remarks |
Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks |
EACL 2021 |
2006.09336 |
|
Sentiment Analysis |
|
|
|
|
|
Please feel free to send me pull requests or email ([email protected]) to add links.
License
![CC0](https://camo.githubusercontent.com/677015bdda99ad2de7a54d05cfd46d9683b3dc3f8da70edb149d413f39a1c60f/687474703a2f2f692e6372656174697665636f6d6d6f6e732e6f72672f702f7a65726f2f312e302f38387833312e706e67)
To the extent possible under law, Simran Khanuja has waived all copyright and related or neighboring rights to this work.