Search Results
The SciQA Scientific Question Answering Benchmark for Scholarly Knowledge
Knowledge graphs have gained increasing popularity in the last decade in science and technology. However, knowledge graphs are currently relatively simple to moderate semantic structures that are mainly a collection of factual statements. Question answering (QA) benchmarks and systems were so far mainly geared towards encyclopedic knowledge graphs such as DBpedia and Wikidata. We present SciQA a scientific QA benchmark for scholarly knowledge. The benchmark leverages the Open Research Knowledge Graph (ORKG) which includes almost 170,000 resources describing research contributions of almost 15,000 scholarly articles from 709 research fields. Following a bottom-up methodology, we first manually developed a set of 100 complex questions that can be answered using this knowledge graph. Furthermore, we devised eight question templates with which we automatically generated further 2465 questions, that can also be answered with the ORKG. The questions cover a range of research fields and question types and are translated into corresponding SPARQL queries over the ORKG. Based on two preliminary evaluations, we show that the resulting SciQA benchmark represents a challenging task for next-generation QA systems. This task is part of the open competitions at the 22nd International Semantic Web Conference 2023 as the Scholarly Question Answering over Linked Data (QALD) Challenge.
Building Scholarly Knowledge Bases with Crowdsourcing and Text Mining
For centuries, scholarly knowledge has been buried in documents. While articles are great to convey the story of scientific work to peers, they make it hard for machines to process scholarly knowledge. The recent proliferation of the scholarly literature and the increasing inability of researchers to digest, reproduce, reuse its content are constant reminders that we urgently need a transformative digitalization of the scholarly literature. Building on the Open Research Knowledge Graph (http://orkg.org) as a concrete research infrastructure, in this talk we present how using crowdsourcing and text mining humans and machines can collaboratively build scholarly knowledge bases, i.e. systems that acquire, curate and publish data, information and knowledge published in the scholarly literature in structured and semantic form. We discuss some key challenges that human and technical infrastructures face as well as the possibilities scholarly knowledge bases enable.
Question Answering on Scholarly Knowledge Graphs
Answering questions on scholarly knowledge comprising text and other artifacts is a vital part of any research life cycle. Querying scholarly knowledge and retrieving suitable answers is currently hardly possible due to the following primary reason: machine inactionable, ambiguous and unstructured content in publications. We present JarvisQA, a BERT based system to answer questions on tabular views of scholarly knowledge graphs. Such tables can be found in a variety of shapes in the scholarly literature (e.g., surveys, comparisons or results). Our system can retrieve direct answers to a variety of different questions asked on tabular data in articles. Furthermore, we present a preliminary dataset of related tables and a corresponding set of natural language questions. This dataset is used as a benchmark for our system and can be reused by others. Additionally, JarvisQA is evaluated on two datasets against other baselines and shows an improvement of two to three folds in performance compared to related methods.
Towards Operational Research Infrastructures with FAIR Data and Services
Environmental research infrastructures aim to provide scientists with facilities, resources and services to enable scientists to effectively perform advanced research. When addressing societal challenges such as climate change and pollution, scientists usually need data, models and methods from different domains to tackle the complexity of the complete environmental system. Research infrastructures are thus required to enable all data, including services, products, and virtual research environments is FAIR for research communities: Findable, Accessible, Interoperable and Reusable. In this last chapter, we conclude and identify future challenges in research infrastructure operation, user support, interoperability, and future evolution.
ORKG: Facilitating the Transfer of Research Results with the Open Research Knowledge Graph
This document is an edited version of the original funding proposal entitled 'ORKG: Facilitating the Transfer of Research Results with the Open Research Knowledge Graph' that was submitted to the European Research Council (ERC) Proof of Concept (PoC) Grant in September 2020 (https://erc.europa.eu/funding/proof-concept). The proposal was evaluated by five reviewers and has been placed after the evaluations on the reserve list. The main document of the original proposal did not contain an abstract.
Case Study: ENVRI Science Demonstrators with D4Science
Whenever a community of practice starts developing an IT solution for its use case(s) it has to face the issue of carefully selecting “the platform” to use. Such a platform should match the requirements and the overall settings resulting from the specific application context (including legacy technologies and solutions to be integrated and reused, costs of adoption and operation, easiness in acquiring skills and competencies). There is no one-size-fits-all solution that is suitable for all application context, and this is particularly true for scientific communities and their cases because of the wide heterogeneity characterising them. However, there is a large consensus that solutions from scratch are inefficient and services that facilitate the development and maintenance of scientific community-specific solutions do exist. This chapter describes how a set of diverse communities of practice efficiently developed their science demonstrators (on analysing and producing user-defined atmosphere data products, greenhouse gases fluxes, particle formation, mosquito diseases) by leveraging the services offered by the D4Science infrastructure. It shows that the D4Science design decisions aiming at streamlining implementations are effective. The chapter discusses the added value injected in the science demonstrators and resulting from the reuse of D4Science services, especially regarding Open Science practices and overall quality of service.
Toward Representing Research Contributions in Scholarly Knowledge Graphs Using Knowledge Graph Cells
There is currently a gap between the natural language expression of scholarly publications and their structured semantic content modeling to enable intelligent content search. With the volume of research growing exponentially every year, a search feature operating over semantically structured content is compelling. Toward this end, in this work, we propose a novel semantic data model for modeling the contribution of scientific investigations. Our model, i.e. the Research Contribution Model (RCM), includes a schema of pertinent concepts highlighting six core information units, viz. Objective, Method, Activity, Agent, Material, and Result, on which the contribution hinges. It comprises bottom-up design considerations made from three scientific domains, viz. Medicine, Computer Science, and Agriculture, which we highlight as case studies. For its implementation in a knowledge graph application we introduce the idea of building blocks called Knowledge Graph Cells (KGC), which provide the following characteristics: (1) they limit the expressibility of ontologies to what is relevant in a knowledge graph regarding specific concepts on the theme of research contributions; (2) they are expressible via ABox and TBox expressions; (3) they enforce a certain level of data consistency by ensuring that a uniform modeling scheme is followed through rules and input controls; (4) they organize the knowledge graph into named graphs; (5) they provide information for the front end for displaying the knowledge graph in a human-readable form such as HTML pages; and (6) they can be seamlessly integrated into any existing publishing process thatsupports form-based input abstracting its semantic technicalities including RDF semantification from the user. Thus RCM joins the trend of existing work toward enhanced digitalization of scholarly publication enabled by an RDF semantification as a knowledge graph fostering the evolution of the scholarly publications beyond written text.
Knowledge Graphs - Working Group Charter (NFDI section-metadata) (1.2)
Knowledge Graphs are a key technology for implementing the FAIR principles in data infrastructures by ensuring interoperability for both humans and machines. The Working Group "Knowledge Graphs" in Section "(Meta)data, Terminologies, Provenance" of the German National Research Data Infrastructure (Nationale Forschungsdateninfrastruktur (NFDI) e.V.) aims to promote the use of knowledge graphs in all NFDI consortia, to facilitate cross-domain data interlinking and federation following the FAIR principles, and to contribute to the joint development of tools and technologies that enable transformation of structured and unstructured data into semantically reusable knowledge across different domains.
TinyGenius: Intertwining natural language processing with microtask crowdsourcing for scholarly knowledge graph creation
As the number of published scholarly articles grows steadily each year, new methods are needed to organize scholarly knowledge so that it can be more efficiently discovered and used. Natural Language Processing (NLP) techniques are able to autonomously process scholarly articles at scale and to create machine readable representations of the article content. However, autonomous NLP methods are by far not sufficiently accurate to create a high-quality knowledge graph. Yet quality is crucial for the graph to be useful in practice. We present TinyGenius, a methodology to validate NLP-extracted scholarly knowledge statements using microtasks performed with crowdsourcing. The scholarly context in which the crowd workers operate has multiple challenges. The explainability of the employed NLP methods is crucial to provide context in order to support the decision process of crowd workers. We employed TinyGenius to populate a paper-centric knowledge graph, using five distinct NLP methods. In the end, the resulting knowledge graph serves as a digital library for scholarly articles.
Semantic and Knowledge Engineering Using ENVRI RM
The ENVRI Reference Model provides architects and engineers with the means to describe the architecture and operational behaviour of environmental and Earth science research infrastructures (RIs) in a standardised way using the standard terminology. This terminology and the relationships between specific classes of concept can be used as the basis for the machine-actionable specification of RIs or RI subsystems. Open Information Linking for Environmental RIs (OIL-E) is a framework for capturing architectural and design knowledge about environmental and Earth science RIs intended to help harmonise vocabulary, promote collaboration and identify common standards and technologies across different research infrastructure initiatives. At its heart is an ontology derived from the ENVRI Reference Model. Using this ontology, RI descriptions can be published as linked data, allowing discovery, querying and comparison using established Semantic Web technologies. It can also be used as an upper ontology by which to connect descriptions of RI entities (whether they be datasets, equipment, processes, etc.) that use other, more specific terminologies. The ENVRI Knowledge Base uses OIL-E to capture information about environmental and Earth science RIs in the ENVRI community for query and comparison. The Knowledge Base can be used to identify the technologies and standards used for particular activities and services and as a basis for evaluating research infrastructure subsystems and behaviours against certain criteria, such as compliance with the FAIR data principles.