{"total":18,"rows":[{"id":"2306.07377","title":"Lost in Translation: Large Language Models in Non-English Content Analysis","created":"2023-06-12","cited_by_count":35,"area":null},{"id":"2310.15135","title":"Quantifying the Dialect Gap and its Correlates Across Languages","created":"2023-10-23","cited_by_count":33,"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":"2412.04497","title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","created":"2024-11-30","cited_by_count":27,"area":null},{"id":"2406.18895","title":"Can we teach language models to gloss endangered languages?","created":"2024-06-27","cited_by_count":14,"area":null},{"id":"2411.11295","title":"Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation","created":"2024-11-18","cited_by_count":12,"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":"2302.04975","title":"Leveraging supplementary text data to kick-start automatic speech recognition system development with limited transcriptions","created":"2023-02-09","cited_by_count":4,"area":null},{"id":"2501.15773","title":"Is It Navajo? Accurate Language Detection in Endangered Athabaskan Languages","created":"2025-01-27","cited_by_count":3,"area":null},{"id":"2503.03186","title":"Designing Speech Technologies for Australian Aboriginal English: Opportunities, Risks and Participation","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2503.03644","title":"DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2412.00218","title":"NushuRescue: Revitalization of the Endangered Nushu Language with AI","created":"2024-11-29","cited_by_count":1,"area":null},{"id":"2206.14969","title":"Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?","created":"2022-06-30","cited_by_count":0,"area":null},{"id":"2210.02545","title":"JoeyS2T: Minimalistic Speech-to-Text Modeling with JoeyNMT","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2409.16884","title":"Shifting from endangerment to rebirth in the Artificial Intelligence Age: An Ensemble Machine Learning Approach for Hawrami Text Classification","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2503.18212","title":"LakotaBERT: A Transformer-based Model for Low Resource Lakota Language","created":"2025-03-23","cited_by_count":0,"area":null},{"id":"2511.14598","title":"Leveraging Digitized Newspapers to Collect Summarization Data in Low-Resource Languages","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.19630","title":"Diacritic Restoration for Low-Resource Indigenous Languages: Case Study with Bribri and Cook Islands M\\=aori","created":"2025-12-22","cited_by_count":0,"area":null}],"next_cursor":null}