bryanwilie
PhD Candidate at The Hong Kong University of Science and Technology @HLTCHKUST @IndoNLP
HKUST, @HLTCHKUST, @IndoNLP Hong Kong SAR
Pinned Repositories
bryanwilie
Hi!
bryanwilie.github.io
ehr_readmission_patient_risk
indonlg
The first-ever vast natural language generation benchmark for Indonesian, Sundanese, and Javanese. We provide multiple downstream tasks, pre-trained IndoGPT and IndoBART models, and a starter code! (EMNLP 2021)
NL-Augmenter
NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations
nusa-crowd
A collaborative project to collect datasets in Indonesian languages.
pick
PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems. This approach reduces hallucination and improves relevance by re-scoring responses, enhancing faithfulness and relevance without extra data or model tuning.
indonlg
The first-ever vast natural language generation benchmark for Indonesian, Sundanese, and Javanese. We provide multiple downstream tasks, pre-trained IndoGPT and IndoBART models, and a starter code! (EMNLP 2021)
indonlu
The first-ever vast natural language processing benchmark for Indonesian Language. We provide multiple downstream tasks, pre-trained IndoBERT models, and a starter code! (AACL-IJCNLP 2020)
nusa-crowd
A collaborative project to collect datasets in Indonesian languages.
bryanwilie's Repositories
bryanwilie/bryanwilie
Hi!
bryanwilie/bryanwilie.github.io
bryanwilie/ehr_readmission_patient_risk
bryanwilie/indonlg
The first-ever vast natural language generation benchmark for Indonesian, Sundanese, and Javanese. We provide multiple downstream tasks, pre-trained IndoGPT and IndoBART models, and a starter code! (EMNLP 2021)
bryanwilie/NL-Augmenter
NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations
bryanwilie/nusa-crowd
A collaborative project to collect datasets in Indonesian languages.
bryanwilie/pick
PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems. This approach reduces hallucination and improves relevance by re-scoring responses, enhancing faithfulness and relevance without extra data or model tuning.
bryanwilie/seacrowd-datahub
A collaborative project to collect datasets in SEA languages, SEA regions, or SEA cultures.
bryanwilie/weak-to-strong