daiyongya

Yong Dai's repositories

This repository contains the data and models from the paper '“Is Whole Word Masking Always Better for Chinese BERT?”: Probing on Chinese Grammatical Error Correction', which is accepted in Findings of ACL 2022, short.

300

MUDA

source codes for 'Adversarial training based multi-source unsupervised domain adaptation for sentiment analysis'

Language:Python200

BG.github.io

it's just a start

Language:HTML000

Chinese-Synonyms

A large high-quality corpus of Chinese synonyms 一个大型、高质量的中文同义词语料库。

Language:Jupyter Notebook000

daiyongya.github.io

Language:HTML000

PRML

PRML algorithms implemented in Python

Language:Jupyter Notebook020