{"total":16,"rows":[{"id":"2210.08523","title":"Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP World","created":"2022-10-16","cited_by_count":55,"area":null},{"id":"2508.09115","title":"SinLlama -- A Large Language Model for Sinhala","created":"2025-08-12","cited_by_count":9,"area":null},{"id":"2403.16571","title":"NSINA: A News Corpus for Sinhala","created":"2024-03-25","cited_by_count":6,"area":null},{"id":"2312.05671","title":"Hate Speech and Offensive Content Detection in Indo-Aryan Languages: A Battle of LSTM and Transformers","created":"2023-12-09","cited_by_count":4,"area":null},{"id":"2412.01293","title":"SiTSE: Sinhala Text Simplification Dataset and Evaluation","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2212.00851","title":"SOLD: Sinhala Offensive Language Dataset","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2412.16365","title":"Overview of the First Workshop on Language Models for Low-Resource Languages (LoResLM 2025)","created":"2024-12-20","cited_by_count":2,"area":null},{"id":"2501.18633","title":"Linguistic Analysis of Sinhala YouTube Comments on Sinhala Music Videos: A Dataset Study","created":"2025-01-28","cited_by_count":2,"area":null},{"id":"2412.02056","title":"A Multi-way Parallel Named Entity Annotated Corpus for English, Tamil and Sinhala","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2511.18146","title":"GeeSanBhava: Sentiment Tagged Sinhala Music Video Comment Data Set","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2510.04750","title":"A Low-Resource Speech-Driven NLP Pipeline for Sinhala Dyslexia Assistance","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2602.02207","title":"Sinhala Physical Common Sense Reasoning Dataset for Global PIQA","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.29221","title":"SiPaKosa: A Comprehensive Corpus of Canonical and Classical Buddhist Texts in Sinhala and Pali","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2608.22922","title":"HelaBERT: Enhancing Sinhala Language Understanding with Dual Pooling Classification Head","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.29680","title":"Confident but Wrong: A Constrained Decoding Diagnostic for Low-Resource Automatic Post-Editing","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2610.05681","title":"Automatic Speech Recognition for Low-Resource Sinhala: A Critical Review of Methods, Challenges, and Future Directions","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}