{"total":28,"rows":[{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2307.03667","title":"Testing the Predictions of Surprisal Theory in 11 Languages","created":"2023-07-07","cited_by_count":77,"area":null},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"area":null},{"id":"2403.20266","title":"Latxa: An Open Language Model and Evaluation Suite for Basque","created":"2024-03-29","cited_by_count":42,"area":null},{"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":"2107.07903","title":"Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan","created":"2021-07-16","cited_by_count":26,"area":null},{"id":"2205.10517","title":"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese","created":"2022-05-21","cited_by_count":14,"area":null},{"id":"2201.05601","title":"A Warm Start and a Clean Crawled Corpus -- A Recipe for Good Language Models","created":"2022-01-14","cited_by_count":13,"area":null},{"id":"2203.08111","title":"Does Corpus Quality Really Matter for Low-Resource Languages?","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2101.11978","title":"Semi-automatic Generation of Multilingual Datasets for Stance Detection in Twitter","created":"2021-01-28","cited_by_count":10,"area":null},{"id":"2109.13664","title":"Multilingual Counter Narrative Type Classification","created":"2021-09-28","cited_by_count":10,"area":null},{"id":"2212.08390","title":"Lessons learned from the evaluation of Spanish Language Models","created":"2022-12-16","cited_by_count":8,"area":null},{"id":"2103.13799","title":"Bertinho: Galician BERT Representations","created":"2021-03-25","cited_by_count":7,"area":null},{"id":"2207.00982","title":"Linguistically inspired roadmap for building biologically reliable protein language models","created":"2022-07-03","cited_by_count":7,"area":null},{"id":"2109.03487","title":"Social Analysis of Young Basque Speaking Communities in Twitter","created":"2021-09-08","cited_by_count":4,"area":null},{"id":"2307.13776","title":"Combating the Curse of Multilinguality in Cross-Lingual WSD by Aligning Sparse Contextualized Word Representations","created":"2023-07-25","cited_by_count":4,"area":null},{"id":"2302.00407","title":"On the Role of Morphological Information for Contextual Lemmatization","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2404.06996","title":"XNLIeu: a dataset for cross-lingual NLI in Basque","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2109.05361","title":"COMBO: State-of-the-Art Morphosyntactic Analysis","created":"2021-09-11","cited_by_count":2,"area":null},{"id":"2205.01506","title":"BasqueParl: A Bilingual Corpus of Basque Parliamentary Transcriptions","created":"2022-05-03","cited_by_count":2,"area":null},{"id":"2309.11165","title":"Assessment of Pre-Trained Models Across Languages and Grammars","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2506.15239","title":"Lost in Variation? Evaluating NLI Performance in Basque and Spanish Geographical Variants","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2403.16968","title":"Evaluating Shortest Edit Script Methods for Contextual Lemmatization","created":"2024-03-25","cited_by_count":1,"area":null},{"id":"2204.12820","title":"LyS_ACoru\\~na at SemEval-2022 Task 10: Repurposing Off-the-Shelf Tools for Sentiment Analysis as Semantic Dependency Parsing","created":"2022-04-27","cited_by_count":0,"area":null},{"id":"2404.12177","title":"EuSQuAD: Automatically Translated and Aligned SQuAD2.0 for Basque","created":"2024-04-18","cited_by_count":0,"area":null},{"id":"2503.01851","title":"Euskarazko lehen C1 ebaluatzaile automatikoa","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2512.03903","title":"BERnaT: Basque Encoders for Representing Natural Textual Diversity","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2603.25189","title":"A Catalog of Basque Dialectal Resources: Online Collections and Standard-to-Dialectal Adaptations","created":"2026-03-26","cited_by_count":0,"area":null}],"next_cursor":null}