{"total":35,"rows":[{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2108.13897","title":"mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset","created":"2021-08-31","cited_by_count":116,"area":null},{"id":"2308.11878","title":"Cabrita: closing the gap for foreign languages","created":"2023-08-23","cited_by_count":25,"area":null},{"id":"2203.03759","title":"IT5: Text-to-text Pretraining for Italian Language Understanding and Generation","created":"2022-03-07","cited_by_count":20,"area":null},{"id":"2304.07880","title":"Sabi\\'a: Portuguese Large Language Models","created":"2023-04-16","cited_by_count":19,"area":null},{"id":"2402.12969","title":"Gl\\'orIA -- A Generative and Open Large Language Model for Portuguese","created":"2024-02-20","cited_by_count":16,"area":null},{"id":"2205.08808","title":"Evaluation of Transfer Learning for Polish with a Text-to-Text Model","created":"2022-05-18","cited_by_count":13,"area":null},{"id":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13,"area":null},{"id":"2205.15172","title":"Billions of Parameters Are Worth More Than In-domain Training Data: A case study in the Legal Case Entailment Task","created":"2022-05-30","cited_by_count":8,"area":null},{"id":"2406.10806","title":"ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2105.06813","title":"A cost-benefit analysis of cross-lingual transfer methods","created":"2021-05-14","cited_by_count":7,"area":null},{"id":"2412.09415","title":"Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2110.10015","title":"DEEPAG\\'E: Answering Questions in Portuguese about the Brazilian Environment","created":"2021-10-19","cited_by_count":5,"area":null},{"id":"2112.01591","title":"PLSUM: Generating PT-BR Wikipedia by Summarizing Multiple Websites","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2201.05658","title":"Sequence-to-Sequence Models for Extracting Information from Registration and Legal Documents","created":"2022-01-14","cited_by_count":2,"area":null},{"id":"2202.04048","title":"Integrating question answering and text-to-SQL in Portuguese","created":"2022-02-08","cited_by_count":2,"area":null},{"id":"2204.10710","title":"Tweets2Stance: Users stance detection exploiting Zero-Shot Learning Algorithms on Tweets","created":"2022-04-22","cited_by_count":2,"area":null},{"id":"2211.05015","title":"Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2212.00587","title":"Embedding generation for text classification of Brazilian Portuguese user reviews: from bag-of-words to transformers","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2309.11259","title":"Sequence-to-Sequence Spanish Pre-trained Language Models","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2309.16844","title":"DeBERTinha: A Multistep Approach to Adapt DebertaV3 XSmall for Brazilian Portuguese Natural Language Processing Task","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2403.12212","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2201.03382","title":"BERT for Sentiment Analysis: Pre-trained and Fine-Tuned Alternatives","created":"2022-01-10","cited_by_count":1,"area":null},{"id":"2209.11035","title":"MonoByte: A Pool of Monolingual Byte-level Language Models","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2211.05025","title":"Local Structure Matters Most in Most Languages","created":"2022-11-09","cited_by_count":1,"area":null},{"id":"2309.10945","title":"Benchmarks for Pir\\'a 2.0, a Reading Comprehension Dataset about the Ocean, the Brazilian Coast, and Climate Change","created":"2023-09-19","cited_by_count":1,"area":null},{"id":"2311.05051","title":"Deep Learning Brasil at ABSAPT 2022: Portuguese Transformer Ensemble Approaches","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2406.04233","title":"FairytaleQA Translated: Enabling Educational Question and Answer Generation in Less-Resourced Languages","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2209.07928","title":"The BLue Amazon Brain (BLAB): A Modular Architecture of Services about the Brazilian Maritime Territory","created":"2022-09-06","cited_by_count":0,"area":null},{"id":"2210.06431","title":"BLAB Reporter: Automated journalism covering the Blue Amazon","created":"2022-10-08","cited_by_count":0,"area":null},{"id":"2306.13315","title":"Abstractive Text Summarization for Resumes With Cutting Edge NLP Transformers and LSTM","created":"2023-06-23","cited_by_count":0,"area":null},{"id":"2509.11496","title":"AKCIT-FN at CheckThat! 2025: Switching Fine-Tuned SLMs and LLM Prompting for Multilingual Claim Normalization","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2602.16607","title":"CitiLink-Summ: Summarization of Discussion Subjects in European Portuguese Municipal Meeting Minutes","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2604.21767","title":"Misinformation Span Detection in Videos via Audio Transcripts","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2608.18138","title":"Language Models for Portuguese: A Systematic Mapping Study","created":"2026-08-03","cited_by_count":0,"area":null}],"next_cursor":null}