Assessing the Contributions of Scientific Articles
Using Transformer-Based Deep Learning
The number of published scientific articles is increasing at an exponential rate per year. Consequently, their claimed contributions may overlap, which is difficult to identify until the reader has reviewed all the works. To optimize the effort in conducting literature reviews for research, e.g., in the field of power engineering, there is a need to develop a tool that can quantitatively assess the contributions of scientific articles. Leveraging the advancements in transformer-based learning algorithms, this project seeks to develop a tool that will evaluatethe quality of a given article.
Quickly Start
01
Preparation
-
OpenAI api key
follow this: How to get an Openai api keys?
-
Nougat api path
install nougat follow this: install Nougat
(This may need pytorch GPU environment, and you can find alternatives on our Settings page first !)
02
Visit the website
-
Click here to visit !
03
Settings
-
Fill in your Openai api key and nougat path.
-
Click Save button.
04
Start to use
-
Upload your PDF paper files.
-
Wait to analyse until the result shown in
the page.
-
This part demonstration see video ahead.