GeneZC's Projects
Aspect Based Sentiment Analysis, PyTorch Implementations. 基于方面的情感分析,使用PyTorch实现。
Resources about Aspect-based Sentiment Analysis (ABSA)
An adversarial ABSA benchmark, including aspect-based sentiment classification and opinion extraction.
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
Repo for AlphaPoet, which appeared in Finals of 2018 International Collegiate Competition for Brain-inspired Computing
Tika GUI with multi-thread
Code and preprocessed dataset for EMNLP 2019 paper titled "Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks"
An easy-to-use model quantization package with user-friendly apis, based on GPTQ algorithm.
Must-read papers on improving efficiency for pre-trained language models.
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins
A simple chatroom based on socket, using java
Dataset from 'Character-based BiLSTM-CRF Incorporating POS and Dictionaries for Chinese Opinion Target Extraction'
A practice on Chinese Named Entity Recognition
Code and dataset for paper "End-to-end Emotion-Cause Pair Extraction via Learning to Link"
Efficient Large Language Models: A Survey
An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.
Code for EMNLP 2022 paper titled "Making Pretrained Language Models Good Long-tailed Learners"
⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡
Code for paper titled "MiniDisc: Minimal Distillation Schedule for Language Model Compression"
Code for paper titled "Towards the Law of Capacity Gap in Distilling Language Models"
Code for ACL 2023 paper titled "Lifting the Curse of Capacity Gap in Distilling Language Models"
Code and dataset for EMNLP 2020 paper titled "A Multi-task Learning Framework for Opinion Triplet Extraction"
Code for SIGIR 2019 paper titled "Syntax-Aware Aspect-Level Sentiment Classification with Proximity-Weighted Convolution Network"
PyTorch 中文文档
Visual Perception for Robocon
Code for EMNLP 2022 paper titled "Sparse Teachers Can Be Dense with Knowledge"
Code and data for COLING 2022 paper titled "Structural Bias For Aspect Sentiment Triplet Extraction"