ScienceGraph focused on transforming scholarly communication by developing a comprehensive knowledge graph-based approach for representing, augmenting, and exploring scientific knowledge. The project advanced through key work packages aimed at addressing the major challenges in bringing scholarly communication to the digital age.
Knowledge Representation (WP1): The project developed a sophisticated model for representing scholarly knowledge using knowledge graphs, capturing research problems, methodologies, results, and scholarly discourse. The model allows for detailed provenance tracking, discourse representation, and the evolution of scientific ideas. The results of this work were disseminated through several high-impact publications and demonstrated in the ORKG (Open Research Knowledge Graph), which now serves as a live platform for representing and querying structured scholarly knowledge.
Knowledge Extraction and Graph Completion (WP2): Significant progress was made in automating the extraction of scholarly information using NLP techniques and large language models. Methods for graph completion were also developed, leveraging graph embeddings and other machine learning techniques to suggest new connections within the knowledge graph. These efforts were validated in large-scale experiments and community-driven crowdsourcing initiatives, resulting in a more comprehensive and interconnected ORKG.
User Interaction and Collaboration (WP3): The team developed adaptive user interfaces and methods for human-machine collaboration, enabling researchers to engage with the knowledge graph more intuitively. Tools for manual curation and quality assurance were also integrated, supported by the ORKG curation grants, which incentivized community involvement in improving the quality of the knowledge graph. These interfaces have been demonstrated through various workshops, raising awareness and adoption.
Exploration and Question Answering (WP4): The project created tools for exploring the ORKG using faceted search and developed the ORKG ASK platform, which allows natural language question answering over a large corpus of scientific literature. Additionally, the SciQA benchmark was established to evaluate scientific question-answering capabilities, setting a new standard in the field.
Testbed Development and Application (WP5): The ScienceGraph testbed was implemented across different scientific domains, including natural sciences, engineering, and environmental sciences. This testbed provided a real-world context for evaluating the project's technological advancements, which were disseminated through targeted case studies, conferences, and the SimpleText track at CLEF 2024.
Exploitation and Dissemination of Results
The project's outcomes have been widely shared through keynotes, publications, workshops, and demonstrators. The ORKG ASK platform and the ORKG itself are freely accessible, fostering widespread use and adoption. The curation grants further promoted active participation from the research community in expanding and refining the ORKG. Key insights and methodologies have been published in leading journals and presented at major conferences, contributing to the global discourse on semantic scholarly communication and AI-driven research tools.
The ScienceGraph project has successfully laid the groundwork for a new paradigm in scholarly communication, making scientific knowledge more accessible, structured, and interactive. Through innovative methodologies and community-driven efforts, the project has delivered substantial tools and platforms that continue to grow and impact the academic landscape.
