greenelab/snorkeling-full-text

This is an upgraded version of the original snorkeling project.

Snorkeling-Full-Text

This is an upgraded version of the original snorkeling project. The goal here is to see if full text will improve distant supervision performance.

Before You Begin

Please make sure you have executed the pubtator repository first as the code in the notebook requires pubtator to have been executed. First run git clone https://github.com/greenelab/pubtator in the same directory that will hold this repository, then follow the instructions that are located in Pubtator's repository.

Installation Instructions

Snorkeling-full-text uses conda as a python package manager. Before moving on to the instructions below, please make sure to have it installed. Download conda here!!

Once everything has been installed, type following command in the terminal:

bash install.sh

Note: There is a bash command within the install.sh that only works on unix systems. If you are on windows (and possibly mac), you should remove that file or execute each command individually. Alternatively for windows users please refer to these installation instructions to enable bash on windows.

You can activate the environment by using the following command:

conda activate snorkeling_full_text

License

Please look at LICENSE.md.

snorkeling-full-text's Issues

And does the full text help???

Asking because I'm doing a project where I was looking at full abstracts, and have recently switched to single sentences for relation extraction because labelling was faster + abstracts seemed like it might be overkill. Very interested on thoughts of the best way to do this.