{"total":20,"rows":[{"id":"2402.17016","title":"Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings","created":"2024-02-26","cited_by_count":21,"area":null},{"id":"2107.11610","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","created":"2021-07-24","cited_by_count":19,"area":null},{"id":"2207.13988","title":"Sequence to sequence pretraining for a less-resourced Slovenian language","created":"2022-07-28","cited_by_count":9,"area":null},{"id":"2307.14134","title":"Developing and Evaluating Tiny to Medium-Sized Turkish BERT Models","created":"2023-07-26","cited_by_count":8,"area":null},{"id":"2112.10553","title":"Training dataset and dictionary sizes matter in BERT models: the case of Baltic languages","created":"2021-12-20","cited_by_count":7,"area":null},{"id":"2202.04994","title":"Slovene SuperGLUE Benchmark: Translation and Evaluation","created":"2022-02-10","cited_by_count":7,"area":null},{"id":"2410.06898","title":"Generative Model for Less-Resourced Language with 1 billion parameters","created":"2024-10-09","cited_by_count":5,"area":null},{"id":"2107.10614","title":"Evaluation of contextual embeddings on less-resourced languages","created":"2021-07-22","cited_by_count":4,"area":null},{"id":"2211.06053","title":"CoRAL: a Context-aware Croatian Abusive Language Dataset","created":"2022-11-11","cited_by_count":4,"area":null},{"id":"2404.05428","title":"Language Models on a Diet: Cost-Efficient Development of Encoders for Closely-Related Languages via Additional Pretraining","created":"2024-04-08","cited_by_count":4,"area":null},{"id":"2405.12929","title":"Code-mixed Sentiment and Hate-speech Prediction","created":"2024-05-21","cited_by_count":4,"area":null},{"id":"2112.04329","title":"JABER and SABER: Junior and Senior Arabic BERt","created":"2021-12-08","cited_by_count":3,"area":null},{"id":"2205.10687","title":"Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Understanding","created":"2022-05-21","cited_by_count":2,"area":null},{"id":"2206.00929","title":"The ParlaSent-BCS dataset of sentiment-annotated parliamentary debates from Bosnia-Herzegovina, Croatia, and Serbia","created":"2022-06-02","cited_by_count":2,"area":null},{"id":"2108.02605","title":"EENLP: Cross-lingual Eastern European NLP Index","created":"2021-08-05","cited_by_count":1,"area":null},{"id":"2603.01691","title":"Building a Strong Instruction Language Model for a Less-Resourced Language","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2304.05468","title":"A Survey of Resources and Methods for Natural Language Processing of Serbian Language","created":"2023-04-11","cited_by_count":0,"area":null},{"id":"2305.08173","title":"Croatian Film Review Dataset (Cro-FiReDa): A Sentiment Annotated Dataset of Film Reviews","created":"2023-05-14","cited_by_count":0,"area":null},{"id":"2305.08187","title":"CroSentiNews 2.0: A Sentence-Level News Sentiment Corpus","created":"2023-05-14","cited_by_count":0,"area":null},{"id":"2506.09560","title":"Towards Open Foundation Language Model and Corpus for Macedonian: A Low-Resource Language","created":"2025-06-11","cited_by_count":0,"area":null}],"next_cursor":null}