{"total":29,"rows":[{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94,"area":null},{"id":"2108.04308","title":"Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development","created":"2021-08-09","cited_by_count":85,"area":null},{"id":"2104.08726","title":"AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages","created":"2021-04-18","cited_by_count":50,"area":null},{"id":"2305.19474","title":"Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers","created":"2023-05-31","cited_by_count":27,"area":null},{"id":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2304.09805","title":"A Survey of Corpora for Germanic Low-Resource Languages and Dialects","created":"2023-04-19","cited_by_count":16,"area":null},{"id":"2203.08954","title":"BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages","created":"2022-03-16","cited_by_count":14,"area":null},{"id":"2104.07483","title":"IndT5: A Text-to-Text Transformer for 10 Indigenous Languages","created":"2021-04-04","cited_by_count":10,"area":null},{"id":"2109.06324","title":"A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space","created":"2021-09-13","cited_by_count":8,"area":null},{"id":"2306.06804","title":"Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2310.10583","title":"Who Are All The Stochastic Parrots Imitating? They Should Tell Us!","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2105.02947","title":"On the logistical difficulties and findings of Jopara Sentiment Analysis","created":"2021-05-06","cited_by_count":4,"area":null},{"id":"2205.06993","title":"Improving Neural Machine Translation of Indigenous Languages with Multilingual Transfer Learning","created":"2022-05-14","cited_by_count":4,"area":null},{"id":"2305.17404","title":"Parallel Corpus for Indigenous Language Translation: Spanish-Mazatec and Spanish-Mixtec","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2404.05365","title":"NLP Progress in Indigenous Latin American Languages","created":"2024-04-08","cited_by_count":4,"area":null},{"id":"2109.05952","title":"Adapting the Tesseract Open-Source OCR Engine for Tamil and Sinhala Legacy Fonts and Creating a Parallel Corpus for Tamil-Sinhala-English","created":"2021-09-13","cited_by_count":2,"area":null},{"id":"2203.09632","title":"Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages","created":"2022-03-17","cited_by_count":2,"area":null},{"id":"2407.17479","title":"The #Somos600M Project: Generating NLP resources that represent the diversity of the languages from LATAM, the Caribbean, and Spain","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2507.00999","title":"La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin America","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2404.08368","title":"Automatic Speech Recognition Advancements for Indigenous Languages of the Americas","created":"2024-04-12","cited_by_count":1,"area":null},{"id":"2407.12620","title":"Harnessing the Power of Artificial Intelligence to Vitalize Endangered Indigenous Languages: Technologies and Experiences","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2503.04405","title":"Comparative Study of Zero-Shot Cross-Lingual Transfer for Bodo POS and NER Tagging Using Gemini 2.0 Flash Thinking Experimental Model","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2205.10411","title":"Educational Tools for Mapuzugun","created":"2022-05-19","cited_by_count":0,"area":null},{"id":"2210.02509","title":"Revisiting Syllables in Language Modelling and their Application on Low-Resource Machine Translation","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2501.09943","title":"Indigenous Languages Spoken in Argentina: A Survey of NLP and Speech Resources","created":"2025-01-17","cited_by_count":0,"area":null},{"id":"2504.01522","title":"Redefining technology for indigenous languages","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2602.16852","title":"Meenz bleibt Meenz, but Large Language Models Do Not Speak Its Dialect","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2605.19066","title":"The Annotation Scarcity Paradox in Low-Resource NLP Evaluation: A Decade of Acceleration and Emerging Constraints","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.22097","title":"Plurification in/of language technology -- The integration of culture in next-generation AI","created":"2026-06-20","cited_by_count":0,"area":null}],"next_cursor":null}