Periodic Reporting for period 4 - ScienceGraph (Knowledge Graph based Representation, Augmentation and Exploration of Scholarly Communication)
Período documentado: 2023-11-01 hasta 2024-04-30
Despite an improved digital access to scientific publications in the last decades, the fundamental principles of scholarly communication remain unchanged and continue to be largely document-based. The document- oriented workflows in science have reached the limits of adequacy as highlighted by recent discussions on the increasing proliferation of scientific literature, the deficiency of peer-review and the reproducibility crisis. In ScienceGRAPH we aim to develop a novel principled model for representing, analysing, augmenting and exploiting scholarly communication in a knowledge-based way by expressing and linking scientific contributions and related artefacts through semantically rich, interlinked knowledge graphs. The model is based on deep semantic representation of scientific contributions, their manual, crowd-sourced and automatic augmentation and finally the intuitive exploration and interaction employing question answering on the resulting ScienceGRAPH base. Currently, knowledge graphs are still confined to representing encyclopaedic, factual information. ScienceGRAPH advances the state-of-the-art by enabling to represent complex interdisciplinary scientific information including fine-grained provenance preservation, discourse capture, evolution tracing and concept drift. Also, we will demonstrate that we can synergistically combine automated extraction and augmentation techniques, with large-scale collaboration to reach an unprecedented level of knowledge graph breadth and depth. As a result, we expect a paradigm shift in the methods of academic discourse towards knowledge-based in- formation flows, which facilitate completely new ways of search and exploration. The efficiency and effectiveness of scholarly communication will significant increase, since ambiguities are reduced, reproducibility is facilitated, redundancy is avoided, provenance and contributions can be better traced and the interconnections of research contributions are made more explicit and transparent.
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.
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.
The transfer of knowledge has not changed fundamentally for many hundreds of years: It is usually document-based - formerly printed on paper as a classic essay and nowadays as PDF. With around 2.5 million new research contributions every year, researchers drown in a flood of pseudo-digitized PDF publications. As a result research is seriously weakened. In ScienceGRAPH, we argue for representing scholarly contributions in a structured and semantic way as a knowledge graph. The advantage is that information represented in a knowledge graph is readable by machines and humans. As an example, we give an overview on the Open Research Knowledge Graph (ORKG), a service demonstrating and implementing this approach. For creating the knowledge graph representation, we rely on a mixture of manual (crowd/expert sourcing) and (semi-)automated techniques. Only with such a combination of human and machine intelligence, we can achieve the required quality of the representation to allow for novel exploration and assistance services for researchers. As a result, a scholarly knowledge graph such as the ORKG can be used to give a condensed overview on the state-of-the-art addressing a particular research quest, for example as a tabular comparison of contributions according to various characteristics of the approaches. Further possible intuitive access interfaces to such scholarly knowledge graphs include domain-specific (chart) visualizations or answering of natural language questions.