{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411},{"id":"1805.10190","title":"Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces","created":"2018-05-25","cited_by_count":377},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"2309.07445","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","created":"2023-09-14","cited_by_count":152},{"id":"1810.13327","title":"Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialog","created":"2018-10-31","cited_by_count":125},{"id":"2308.11466","title":"SONAR: Sentence-Level Multimodal and Language-Agnostic Representations","created":"2023-08-22","cited_by_count":108},{"id":"1804.00320","title":"Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension","created":"2018-04-01","cited_by_count":74},{"id":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71},{"id":"2406.06371","title":"mHuBERT-147: A Compact Multilingual HuBERT Model","created":"2024-06-10","cited_by_count":66},{"id":"2105.07316","title":"From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding","created":"2021-05-15","cited_by_count":43},{"id":"2311.07978","title":"AfroBench: How Good are Large Language Models on African Languages?","created":"2023-11-14","cited_by_count":43},{"id":"2401.05632","title":"Natural Language Processing for Dialects of a Language: A Survey","created":"2024-01-11","cited_by_count":40},{"id":"2109.12072","title":"SD-QA: Spoken Dialectal Question Answering for the Real World","created":"2021-09-24","cited_by_count":38},{"id":"2303.18110","title":"The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR","created":"2023-03-31","cited_by_count":36},{"id":"2104.08524","title":"Multilingual and Cross-Lingual Intent Detection from Spoken Data","created":"2021-04-17","cited_by_count":35},{"id":"2406.13469","title":"Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks","created":"2024-06-19","cited_by_count":34},{"id":"2103.11401","title":"SwissDial: Parallel Multidialectal Corpus of Spoken Swiss German","created":"2021-03-21","cited_by_count":26},{"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},{"id":"2408.03900","title":"Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond","created":"2024-08-07","cited_by_count":20},{"id":"2304.10158","title":"Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages","created":"2023-04-20","cited_by_count":19},{"id":"2305.04572","title":"Putting Natural in Natural Language Processing","created":"2023-05-08","cited_by_count":17},{"id":"2112.05842","title":"Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems","created":"2021-12-10","cited_by_count":15},{"id":"2305.20080","title":"Findings of the VarDial Evaluation Campaign 2023","created":"2023-05-31","cited_by_count":14},{"id":"2407.09818","title":"AraFinNLP 2024: The First Arabic Financial NLP Shared Task","created":"2024-07-13","cited_by_count":12},{"id":"2406.19564","title":"Voices Unheard: NLP Resources and Models for Yor\\`ub\\'a Regional Dialects","created":"2024-06-27","cited_by_count":11},{"id":"2306.08502","title":"ITALIC: An Italian Intent Classification Dataset","created":"2023-06-14","cited_by_count":10},{"id":"2412.09084","title":"Evaluating Pixel Language Models on Non-Standardized Languages","created":"2024-12-12","cited_by_count":10},{"id":"2303.17683","title":"Fine-Tuning BERT with Character-Level Noise for Zero-Shot Transfer to Dialects and Closely-Related Languages","created":"2023-03-30","cited_by_count":9},{"id":"2310.02973","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","created":"2023-10-04","cited_by_count":9},{"id":"2506.12181","title":"Generative or Discriminative? Revisiting Text Classification in the Era of Transformers","created":"2025-06-13","cited_by_count":9},{"id":"2506.17611","title":"OpusLM: A Family of Open Unified Speech Language Models","created":"2025-06-21","cited_by_count":9},{"id":"2509.20045","title":"Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks","created":"2025-09-24","cited_by_count":9},{"id":"2304.11075","title":"Spaiche: Extending State-of-the-Art ASR Models to Swiss German Dialects","created":"2023-04-20","cited_by_count":8},{"id":"2404.19310","title":"Does Whisper understand Swiss German? An automatic, qualitative, and human evaluation","created":"2024-04-30","cited_by_count":8},{"id":"2501.08502","title":"Adapting Whisper for Regional Dialects: Enhancing Public Services for Vulnerable Populations in the United Kingdom","created":"2025-01-15","cited_by_count":7},{"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},{"id":"2404.07304","title":"We're Calling an Intervention: Exploring Fundamental Hurdles in Adapting Language Models to Nonstandard Text","created":"2024-04-10","cited_by_count":6},{"id":"2409.06372","title":"SpeechTaxi: On Multilingual Semantic Speech Classification","created":"2024-09-10","cited_by_count":6},{"id":"2411.05872","title":"Dialectal Coverage And Generalization in Arabic Speech Recognition","created":"2024-11-07","cited_by_count":6},{"id":"2307.07295","title":"Towards dialect-inclusive recognition in a low-resource language: are balanced corpora the answer?","created":"2023-07-14","cited_by_count":5},{"id":"2212.13015","title":"Skit-S2I: An Indian Accented Speech to Intent dataset","created":"2022-12-26","cited_by_count":4},{"id":"2305.09652","title":"The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation","created":"2023-05-16","cited_by_count":4},{"id":"2402.02078","title":"Exploring the Robustness of Task-oriented Dialogue Systems for Colloquial German Varieties","created":"2024-02-03","cited_by_count":4},{"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},{"id":"2505.19606","title":"Languages in Whisper-Style Speech Encoders Align Both Phonetically and Semantically","created":"2025-05-26","cited_by_count":3},{"id":"2501.03870","title":"Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detection","created":"2025-01-07","cited_by_count":2}],"next_cursor":null}