{"total":15,"rows":[{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2310.16248","title":"GlotLID: Language Identification for Low-Resource Languages","created":"2023-10-24","cited_by_count":39,"area":null},{"id":"2402.11968","title":"What Do Dialect Speakers Want? A Survey of Attitudes Towards Language Technology for German Dialects","created":"2024-02-19","cited_by_count":21,"area":null},{"id":"2406.19564","title":"Voices Unheard: NLP Resources and Models for Yor\\`ub\\'a Regional Dialects","created":"2024-06-27","cited_by_count":11,"area":null},{"id":"2403.12749","title":"Sebastian, Basti, Wastl?! Recognizing Named Entities in Bavarian Dialectal Data","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2403.10293","title":"MaiBaam: A Multi-Dialectal Bavarian Universal Dependency Treebank","created":"2024-03-15","cited_by_count":7,"area":null},{"id":"2506.02894","title":"A Multi-Dialectal Dataset for German Dialect ASR and Dialect-to-Standard Speech Translation","created":"2025-06-03","cited_by_count":7,"area":null},{"id":"2601.18026","title":"CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data","created":"2026-01-25","cited_by_count":6,"area":null},{"id":"2501.03863","title":"Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study","created":"2025-01-07","cited_by_count":3,"area":null},{"id":"2509.17855","title":"Make Every Letter Count: Building Dialect Variation Dictionaries from Monolingual Corpora","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2402.04028","title":"AlbNews: A Corpus of Headlines for Topic Modeling in Albanian","created":"2024-02-06","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":"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":"2602.21377","title":"Beyond Subtokens: A Rich Character Embedding for Low-resource and Morphologically Complex Languages","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.28213","title":"\\textit{Versteasch du mi?} Computational and Socio-Linguistic Perspectives on GenAI, LLMs, and Non-Standard Language","created":"2026-03-30","cited_by_count":0,"area":null}],"next_cursor":null}