{"total":32,"rows":[{"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":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2308.02976","title":"Spanish Pre-trained BERT Model and Evaluation Data","created":"2023-08-06","cited_by_count":81,"area":null},{"id":"2210.03992","title":"Generative Language Models for Paragraph-Level Question Generation","created":"2022-10-08","cited_by_count":28,"area":null},{"id":"2101.10421","title":"English Machine Reading Comprehension Datasets: A Survey","created":"2021-01-25","cited_by_count":26,"area":null},{"id":"2305.15020","title":"An Efficient Multilingual Language Model Compression through Vocabulary Trimming","created":"2023-05-24","cited_by_count":20,"area":null},{"id":"2202.06219","title":"PQuAD: A Persian Question Answering Dataset","created":"2022-02-13","cited_by_count":14,"area":null},{"id":"2106.02834","title":"MergeDistill: Merging Pre-trained Language Models using Distillation","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2305.17416","title":"A Practical Toolkit for Multilingual Question and Answer Generation","created":"2023-05-27","cited_by_count":10,"area":null},{"id":"2101.10649","title":"Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks","created":"2021-01-26","cited_by_count":8,"area":null},{"id":"2207.09150","title":"On the Usability of Transformers-based models for a French Question-Answering task","created":"2022-07-19","cited_by_count":8,"area":null},{"id":"2109.13209","title":"FQuAD2.0: French Question Answering and knowing that you know nothing","created":"2021-09-27","cited_by_count":7,"area":null},{"id":"2404.04487","title":"KazQAD: Kazakh Open-Domain Question Answering Dataset","created":"2024-04-06","cited_by_count":7,"area":null},{"id":"2204.09145","title":"ALBETO and DistilBETO: Lightweight Spanish Language Models","created":"2022-04-19","cited_by_count":6,"area":null},{"id":"2312.00567","title":"Explanatory Argument Extraction of Correct Answers in Resident Medical Exams","created":"2023-12-01","cited_by_count":6,"area":null},{"id":"2205.10233","title":"RigoBERTa: A State-of-the-Art Language Model For Spanish","created":"2022-04-27","cited_by_count":5,"area":null},{"id":"2312.04362","title":"PCoQA: Persian Conversational Question Answering Dataset","created":"2023-12-07","cited_by_count":5,"area":null},{"id":"2404.05333","title":"PORTULAN ExtraGLUE Datasets and Models: Kick-starting a Benchmark for the Neural Processing of Portuguese","created":"2024-04-08","cited_by_count":5,"area":null},{"id":"2404.17194","title":"TIGQA:An Expert Annotated Question Answering Dataset in Tigrinya","created":"2024-04-26","cited_by_count":5,"area":null},{"id":"2310.13290","title":"Interpreting Indirect Answers to Yes-No Questions in Multiple Languages","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2211.13794","title":"Question Answering and Question Generation for Finnish","created":"2022-11-24","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":"2408.16928","title":"ACE-2005-PT: Corpus for Event Extraction in Portuguese","created":"2024-08-29","cited_by_count":1,"area":null},{"id":"2501.05963","title":"Finnish SQuAD: A Simple Approach to Machine Translation of Span Annotations","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2306.16176","title":"SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2401.03590","title":"Building Efficient and Effective OpenQA Systems for Low-Resource Languages","created":"2024-01-07","cited_by_count":0,"area":null},{"id":"2404.08617","title":"Synthetic Dataset Creation and Fine-Tuning of Transformer Models for Question Answering in Serbian","created":"2024-04-12","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":"2404.16257","title":"Translation of Multifaceted Data without Re-Training of Machine Translation Systems","created":"2024-04-25","cited_by_count":0,"area":null},{"id":"2406.10172","title":"Datasets for Multilingual Answer Sentence Selection","created":"2024-06-14","cited_by_count":0,"area":null},{"id":"2412.20212","title":"Building a Rich Dataset to Empower the Persian Question Answering Systems","created":"2024-12-28","cited_by_count":0,"area":null},{"id":"2511.16470","title":"Arctic-Extract Technical Report","created":"2025-11-20","cited_by_count":0,"area":null}],"next_cursor":null}