FilBench: Can LLMs Understand and Generate Filipino?
Paper • 2508.03523 • Published • 1
Filipino NLP
My collection of works and collabs related to Filipino NLP. For more info, please visit: https://ljvmiranda921.github.io/filipino-nlp/
Note We created a benchmark, FilBench, for evaluating language models on several Filipino-centric tasks (EMNLP 2025).
-
FilBench Leaderboard
🥇5An Open LLM Leaderboard for Filipino
Developing a Named Entity Recognition Dataset for Tagalog
Paper • 2311.07161 • Published • 2Note Here, we introduce TLUnified-NER, a gold-standard dataset for Tagalog NER (SEALP 2023).
-
ljvmiranda921/tlunified-ner
Viewer • Updated • 9.4k • 69 • 6
calamanCy: A Tagalog Natural Language Processing Toolkit
Paper • 2311.07171 • PublishedNote We created an open-source tool for Tagalog NLP based on spaCy (NLP-OSS 2023).
-
ljvmiranda921/tl_calamancy_trf-0.1.0
Token Classification • Updated • 31 • 5 -
ljvmiranda921/tl_calamancy_md
Token Classification • Updated • 132 -
ljvmiranda921/tl_calamancy_lg
Token Classification • Updated • 16
The UD-NewsCrawl Treebank: Reflections and Challenges from a Large-scale Tagalog Syntactic Annotation Project
Paper • 2505.20428 • PublishedNote We introduce the largest Tagalog treebank to date, 100x larger than previous treebanks (ACL 2025).
-
filbench/UD_Tagalog-NewsCrawl
Viewer • Updated • 15.6k • 95 • 1