{"total":19,"rows":[{"id":"2503.07920","title":"Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2311.07161","title":"Developing a Named Entity Recognition Dataset for Tagalog","created":"2023-11-13","cited_by_count":7,"area":null},{"id":"2210.05610","title":"MTet: Multi-domain Translation for English and Vietnamese","created":"2022-10-11","cited_by_count":5,"area":null},{"id":"2502.14911","title":"Batayan: A Filipino NLP benchmark for evaluating Large Language Models","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2204.03251","title":"Towards Automatic Construction of Filipino WordNet: Word Sense Induction and Synset Induction Using Sentence Embeddings","created":"2022-04-07","cited_by_count":3,"area":null},{"id":"2311.07171","title":"calamanCy: A Tagalog Natural Language Processing Toolkit","created":"2023-11-13","cited_by_count":3,"area":null},{"id":"2508.03523","title":"FilBench: Can LLMs Understand and Generate Filipino?","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2204.02653","title":"Using Synthetic Data for Conversational Response Generation in Low-resource Settings","created":"2022-04-06","cited_by_count":2,"area":null},{"id":"2506.07249","title":"Bias Attribution in Filipino Language Models: Extending a Bias Interpretability Metric for Application on Agglutinative Languages","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2403.14990","title":"MasonTigers at SemEval-2024 Task 1: An Ensemble Approach for Semantic Textual Relatedness","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2602.14466","title":"Robust Bias Evaluation with FilBBQ: A Filipino Bias Benchmark for Question-Answering Language Models","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2210.02675","title":"Look Ma, Only 400 Samples! Revisiting the Effectiveness of Automatic N-Gram Rule Generation for Spelling Normalization in Filipino","created":"2022-10-06","cited_by_count":0,"area":null},{"id":"2310.12778","title":"Label-Aware Automatic Verbalizer for Few-Shot Text Classification","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2310.16322","title":"Samsung R&D Institute Philippines at WMT 2023","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2505.18995","title":"FiLLM -- A Filipino-optimized Large Language Model based on Southeast Asia Large Language Model (SEALLM)","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2505.20428","title":"The UD-NewsCrawl Treebank: Reflections and Challenges from a Large-scale Tagalog Syntactic Annotation Project","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2605.26007","title":"Forgotten Words: Benchmarking NeoBERT for Dementia Detection in Low-Resource Conversational Filipino and English Speech","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.15144","title":"PACUTE: Phonology-, Affix-, and Character-level Understanding of Tokens for Filipino","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2610.17597","title":"TDR: Tagalog Diacritic Restoration Dataset","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}