rz-zhang

Active-NER

Bayesian Deep Active Learning for Named entity recognition (NER)

Active-NLP

Bayesian Deep Active Learning for Natural Language Processing Tasks

Attention-PyTorch

注意力机制实践

Auto_KVC

awesome-multimodal-ml

Reading list for research topics in multimodal machine learning

dynamic_social_networks

CSC 555 Social Computing - Project | Social network analysis traditionally makes use of unweighted graphs, with no other information between peers except for acknowledgement of existence of a link. In our work, we attempt to construct a weighted graph using user interactions, where weights represent the degree of recent frequent interaction. We reward the links among users for each interaction and also decay those rewards over time. We therefore, use such recent interactions as evidence of a stronger bond and assign weights accordingly. Finally, we optimize our values of rewards and decay using some power laws which are exhibited by real world weighted networks

ExHalder

Module-based-few-shot-event-extraction

PRBoost

The codes for our ACL'22 paper: PRBOOST: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning.

SeqMix

The repository for our EMNLP'20 paper SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup.

rz-zhang/Attention-PyTorch

注意力机制实践