Xiaoya Li's repositories
Chinese-BERT-wwm
Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）
CorefQA
This repo contains the code for ACL2020 paper "Coreference Resolution as Query-based Span Prediction"
CorefQA-pytorch
A PyTorch implementation of the CorefQA Model.
delight
DeLighT: Very Deep and Light-Weight Transformers
drqa-datasets
The QA datasets used for DrQA evaluation.
e2e-metrics
E2E NLG Challenge Evaluation metrics
LAMA
LAnguage Model Analysis
LDOCE-Pronunciation-Audio-Downloader
A Node.js tool to download both British and American pronunciation of vocabularies from Longman Dictionary of Contemporary English (http://www.ldoceonline.com)
Megatron-LM
Ongoing research training transformer language models at scale, including: BERT & GPT-2
NCRFpp
NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.
PRML
PRML algorithms implemented in Python
RefQA
The implementation of the paper "Harvesting and Refining Question-Answer Pairs for Unsupervised QA"
simclr
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners