ReadMe2KG: Github ReadMe to Knowledge Graph #Challenge has been published as part of the Natural Scientific Language Processing and Research Knowledge Graphs #NSLP2025 workshop co-located with #eswc2025. This #NER task aims to complement the NDFI4DataScience KG via information extraction from GitHub README files.
task description: https://nfdi4ds.github.io/nslp2025/docs/readme2kg_shared_task.html
website: https://www.codabench.org/competitions/5396/
@eswc_conf @GenAsefa @shufan @NFDI4DS #NFDIrocks #knowledgegraphs #semanticweb #nlp #informationextraction
![Readme2KG Challenge website screen shot:
The vision of NFDI4DataScience (NFDI4DS) is to support all steps of the complex and interdisciplinary research data lifecycle, including collecting/creating, processing, analyzing, publishing, archiving, and reusing resources in Data Science and Artificial Intelligence. GitHub is a popular platform for hosting and collaborating on software projects. In the context of research, authors can use GitHub repositories to share the datasets, models, and source code of experiments in the paper. These repositories can provide implementation details and facilitate the exploration and reproduction of research results. Each GitHub repository typically includes a README.md file, which serves as an introductory document for the project. READMEs are usually written in Markdown format and provide key information such as the project’s purpose, setup instructions, usage examples, and often links to the original research paper. Aiming to enhance the NDFI4DS-KG[1] with information from GitHub README files, a fine-grained Named Entity Recognition task is proposed.](https://cdn.masto.host/sigmoidsocial/media_attachments/files/113/911/853/539/988/035/original/3685008c425e43d8.png)
@lysander07 Alt text: A screenshot of the README2KG competition website shows details about the competition, including its organizer, current phase end date (February 15th, 2025), server time, and docker image. There are sections for "Get Started," "Phases," "My Submissions," "Results," and "Forum." The main content describes a named entity recognition task using approximately 160 README.md files as a dataset, focusing on 10 entity types from the NFDI4DS Ontology. Participant numbers and submissions are displayed as 5 and 1 respectively.
Provided by @altbot, generated using Gemini
@lysander07 @eswc_conf @GenAsefa @shufan @NFDI4DS This sounded interesting until I noticed that it’s *just* named entity recognition? Knowledge graphs are more than entities, they’re entities, relations, and attributes!