README.md

BERT for Vietnamese Law

Apply for Task 1: Legal Document Retrieval on ALQAC 2021 dataset

The model achieved 0.80 on the leaderboard(1st place score is 0.88).

We use vibert4news as based model and fine-tune on our own Vietnamese law dataset.

We use word sentencepiece, use basic bert tokenization and same config with bert base with lowercase = False.