{"total":14,"rows":[{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148,"area":null},{"id":"2403.02901","title":"A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods","created":"2024-03-05","cited_by_count":102,"area":null},{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57,"area":null},{"id":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2110.14566","title":"IndoNLI: A Natural Language Inference Dataset for Indonesian","created":"2021-10-27","cited_by_count":24,"area":null},{"id":"2402.08638","title":"SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages","created":"2024-02-13","cited_by_count":16,"area":null},{"id":"2403.09362","title":"Komodo: A Linguistic Expedition into Indonesia's Regional Languages","created":"2024-03-14","cited_by_count":10,"area":null},{"id":"2411.04585","title":"The State and Fate of Summarization Datasets: A Survey","created":"2024-11-07","cited_by_count":3,"area":null},{"id":"2412.01186","title":"SailCompass: Towards Reproducible and Robust Evaluation for Southeast Asian Languages","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2310.08085","title":"Low-Resource Clickbait Spoiling for Indonesian via Question Answering","created":"2023-10-12","cited_by_count":2,"area":null},{"id":"2403.12799","title":"Investigating Text Shortening Strategy in BERT: Truncation vs Summarization","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2403.12563","title":"Simple Hack for Transformers against Heavy Long-Text Classification on a Time- and Memory-Limited GPU Service","created":"2024-03-19","cited_by_count":0,"area":null},{"id":"2610.19497","title":"Structure-Preserving Document-Level Data Augmentation via Discourse Parsing","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}