Hi, there!
I am a PhD student at the University of Exeter. I am currently working on NLP adversarial attacks and defense, etc.
Here are some demos you can try on Huggingface Space:
- SuperResolutionAnimeDiffusion
- Aspect term extraction & sentiment classification (English, Chinese, Arabic, Dutch, French, Russian, Spanish, Turkish, etc.)
- Aspect-based sentiment classification (Multilingual) （English, Chinese, etc.）
These demos are powered by PyABSA, which is one of the most easy-to-use open-source tools for aspect-based sentiment analysis(a.k.a ABSA). PyABSA contains our state-of-the-art models for ABSA, which can be found on Paperswithcode.
Here are some of my open source tools that may help you
- PyABSA: State-of-the-art models and simplified interface for ABSA
- FindFile: A simple tool to help find your file wherever it locates
- Autocuda: Help your model to find available cuda device without manually
nvidia-smi - Metric-Visualizer: Help you to easily make paper beautiful plots
- ABSADatasets DPT: This is a web-based dataset annotation tool that can help you easily make an ABSA dataset and train it using PyABSA.
- Text Augmentation Tool: it can achieve 1-2% or at most 5% absolute improvement based on existing datasets and models
- Adversarial defense under submission
- Image Resolution Magnifier To magnify your image, currently for animes only
- [More are on the way]
About Me
Visitors