The official implementation of "EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa"
$ git clone https://github.com/tae898/erc.gitBERT classification model for processing texts longer than 512 tokens. Text is first divided into smaller chunks and after feeding them to BERT, intermediate results are pooled. The implementation allows fine-tuning.
▲ +7 ★ this week
BertViz: Visualize Attention in Transformer Models
⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.
▲ +1 ★ this week
Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）
▲ +1 ★ this week
A Unified Library for Parameter-Efficient and Modular Transfer Learning
Data from GitHub · snapshot Nov 13, 2026