{"total":46,"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":"2208.07864","title":"BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification","created":"2022-08-16","cited_by_count":16,"area":null},{"id":"2402.07446","title":"Quality Does Matter: A Detailed Look at the Quality and Utility of Web-Mined Parallel Corpora","created":"2024-02-12","cited_by_count":13,"area":null},{"id":"2507.18264","title":"Zero-shot OCR Accuracy of Low-Resourced Languages: A Comparative Analysis on Sinhala and Tamil","created":"2025-07-24","cited_by_count":9,"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":"2501.00529","title":"Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches","created":"2024-12-31","cited_by_count":6,"area":null},{"id":"2308.02234","title":"Sinhala-English Parallel Word Dictionary Dataset","created":"2023-08-04","cited_by_count":4,"area":null},{"id":"2406.06021","title":"Shoulders of Giants: A Look at the Degree and Utility of Openness in NLP Research","created":"2024-06-10","cited_by_count":4,"area":null},{"id":"2112.00468","title":"Seeking Sinhala Sentiment: Predicting Facebook Reactions of Sinhala Posts","created":"2021-12-01","cited_by_count":3,"area":null},{"id":"2412.01293","title":"SiTSE: Sinhala Text Simplification Dataset and Evaluation","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2501.05816","title":"IndoNLP 2025: Shared Task on Real-Time Reverse Transliteration for Romanized Indo-Aryan languages","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2502.19074","title":"Improving the quality of Web-mined Parallel Corpora of Low-Resource Languages using Debiasing Heuristics","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2201.03941","title":"Sentiment Analysis with Deep Learning Models: A Comparative Study on a Decade of Sinhala Language Facebook Data","created":"2022-01-11","cited_by_count":2,"area":null},{"id":"2205.08722","title":"Data Augmentation to Address Out-of-Vocabulary Problem in Low-Resource Sinhala-English Neural Machine Translation","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2210.14472","title":"Sinhala Sentence Embedding: A Two-Tiered Structure for Low-Resource Languages","created":"2022-10-26","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":"2509.17912","title":"SiDiaC: Sinhala Diachronic Corpus","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2311.10436","title":"Sinhala-English Word Embedding Alignment: Introducing Datasets and Benchmark for a Low Resource Language","created":"2023-11-17","cited_by_count":1,"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":"2501.05700","title":"Linguistic Entity Masking to Improve Cross-Lingual Representation of Multilingual Language Models for Low-Resource Languages","created":"2025-01-10","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":"2602.09866","title":"SinFoS: A Parallel Dataset for Translating Sinhala Figures of Speech","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2603.04854","title":"SinhaLegal: A Benchmark Corpus for Information Extraction and Analysis in Sinhala Legislative Texts","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.10861","title":"SiDiaC-v.2.0: Sinhala Diachronic Corpus Version 2.0","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2603.25309","title":"Separate Before You Compress: The WWHO Tokenization Architecture","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2607.22456","title":"grapheme-kit: Grapheme-Level Metrics and Text Processing for Multilingual NLP","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2609.29511","title":"EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2504.02178","title":"Subasa - Adapting Language Models for Low-resourced Offensive Language Detection in Sinhala","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2507.09245","title":"Swa-bhasha Resource Hub: Romanized Sinhala to Sinhala Transliteration Systems and Data Resources","created":"2025-07-12","cited_by_count":0,"area":null},{"id":"2508.09091","title":"Utilizing Multilingual Encoders to Improve Large Language Models for Low-Resource Languages","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2511.13040","title":"How Good is BLI as an Alignment Measure: A Study in Word Embedding Paradigm","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2512.05414","title":"LMSpell: Spell Correction with Pre-Trained Language Models","created":"2025-12-05","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":"2603.10613","title":"MUNIChus: Multilingual News Image Captioning Benchmark","created":"2026-03-11","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":"2606.25518","title":"Fault of Our Stars: Behavioral Drivers of Rating-Sentiment Incongruence","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.05260","title":"Shifting from Discrete to Continuous Reference Data: QSM-Derived Horizontal Tree Biomass Distribution for Deep Learning Biomass Estimation","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.20365","title":"Trilingual Topic Modeling of Sri Lankan Parliamentary Debates","created":"2026-06-18","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":"2609.08609","title":"Dynamics of Meaning: Towards the Evaluation of Diachronic Semantic Change in Sinhala","created":"2026-09-08","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":"2609.32382","title":"PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36131","title":"A Character-Level Neural Approach to Sinhala Sandhi Splitting","created":"2026-09-28","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},{"id":"2610.11389","title":"Fact over Fiction: Detection of Pathological Hallucinations in Sinhala-to-English Neural Machine Translation","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}