The UD-NewsCrawl Treebank: Reflections and Challenges from a Large-scale Tagalog Syntactic Annotation Project
Paper
•
2505.20428
•
Published
Universal Dependencies for Tagalog
Models and dependency parsers for Tagalog using the UD_NewsCrawl dataset
-
-
UD-Filipino/UD_Tagalog-NewsCrawl
Viewer • Updated • 15.6k • 107 • 1
UD-Filipino/tl_spacy_baseline
Token Classification • Updated • 2Note spaCy pipeline using a transition-based parser (baseline)
UD-Filipino/tl_xlm_roberta_transition
Token Classification • Updated • 3Note spaCy pipeline using context-sensitive vectors from XLM-RoBERTa and a transition-based parser.
UD-Filipino/tl_roberta_tgl_transition
Token Classification • Updated • 2Note spaCy pipeline using context-sensitive vectors from RoBERTa-Tagalog and a transition-based parser
UD-Filipino/tl_mdeberta_v3_transition
Token Classification • Updated • 5Note spaCy pipeline using context-sensitive vecotrs from mDeBERTa-v3 and a transition-based parser
UD-Filipino/tl_fasttext_transition
Token Classification • Updated • 4Note spaCy pipeline using fastText word embeddings and a transition-based parser
UD-Filipino/tl_hash_transition
Token Classification • Updated • 8Note spaCy pipeline using multi hash embeddings and a transition-based parser