Join a competition on Scholarly Knowledge Graph Generation

Together with CORE we’re having a Shared Task competition focused on leveraging NLP tools and models to develop Knowledge Graphs. All of that is a part of the Third workshop on Scholarly Document Processing (SDP2022), being held in association with the prestigious International Conference on Computational Linguistics (COLING) 2022.

This is a great opportunity for students and researchers to contribute and help solve real world problems in the Open Access landscape. Additionally, successful teams will be invited to present their results at a prestigious international conference and their results and methods will be published in the conference proceedings.

Extracting Research Themes

For this task, teams will be asked to develop a model that can identify and label research papers with a research theme. There will be a total of 36 themes, each paper will be labeled with a single theme.

Competitors will be provided with 2 files, train.csv and test.csv. The train.csv file will contain the details for each paper in question and the class label (the research theme). The test.csv file should then be used for evaluating your trained models.

Task participants are required to:

Develop methods addressing the task and submit the results via Kaggle
Document and submit their method as a short paper as specified on the SDP 2022 website
Provide source code for each method

The task is now LIVE. Hurry up and join! You can read the details at: https://www.kaggle.com/competitions/sdp2022-scholarly-knowledge-graph-generation/overview

The deadline is 31 July. You can submit your results to us (ronin@iris.ai). After submitting there will be a screening process and the winner will be invited to the conference to present it (October 16-17).

Good luck and science the shit out of it!