5 results
Search Results
Now showing 1 - 5 of 5
- ItemTinyGenius: Intertwining natural language processing with microtask crowdsourcing for scholarly knowledge graph creation(New York,NY,United States : Association for Computing Machinery, 2022) Oelen, Allard; Stocker, Markus; Auer, Sören; Aizawa, AkikoAs 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.
- ItemCorona-Krise? - Welche Krise? Zum Umgang mit einer Pandemie(Freiburg, Br. : LJ-Verlag, 2022) Diebold, Steffen M.The corona pandemic poses major challenges for society. Many people lack (basic) scientific knowledge. They are skeptical and distrust fundamental research principles and concepts. Esotericism and superstition replace them access to reality. Not only facts are recently considered "alternative". Pseudo-scientific healing methods and occult procedures have long been presented to the public as equivalent alternatives to modern medicine, despite the lack of evidence of their effectiveness. Just as if reason or nonsense were just a question of personal taste, a different world view. Seconded by talk of an "exaggeratedly scientific world view", empiricism and logic were systematically defamed. As a result of this distorted picture, all kinds of conspiracy theories are now rampant. Spiritual healers, seers, shamans, charlatans, quacks, sectarians, and zealots of all stripes and persuasions are in demand. Diffuse pandemic management and miserable communication do the rest and contribute to the fact that infection control measures are often flatly rejected and vaccination rates can hardly be increased significantly.
- ItemElectrically conductive and piezoresistive polymer nanocomposites using multiwalled carbon nanotubes in a flexible copolyester: Spectroscopic, morphological, mechanical and electrical properties(Amsterdam [u.a.] : Elsevier, 2022) Dhakal, Kedar Nath; Khanal, Santosh; Krause, Beate; Lach, Ralf; Grellmann, Wolfgang; Le, Hai Hong; Das, Amit; Wießner, Sven; Heinrich, Gert; Pionteck, Jürgen; Adhikari, RameshwarNanocomposites of multiwalled carbon nanotubes (MWCNTs) with poly(butylene adipate-co-terephthalate) (PBAT), a flexible aromatic–aliphatic copolyester, were prepared by melt mixing followed by compression moulding to investigate their spectroscopic, morphological, mechanical and electrical properties. A comparison of the Fourier transform infrared (FTIR) spectra of the neat polymer matrix and the composites showed no difference, implying a physical mixing of the matrix and the filler. A morphological investigation revealed the formation of a continuous and interconnected MWCNT network embedded in the polymer matrix with partial agglomeration. Increasing Martens hardness and indentation modulus and decreasing maximum indentation depth with increasing filler concentration demonstrated the reinforcement of the polymer by the MWCNTs. A volume resistivity of 4.6 × 105 Ω cm of the materials was achieved by the incorporation of only 1 wt.-% of the MWCNTs, which confirmed a quite low percolation threshold (below 1 wt.-%) of the nanocomposites. The electrical volume resistivity of the flexible nanocomposites was achieved up to 1.6 × 102 Ω cm, depending on the filler content. The elongation at the break of the nanocomposites at 374% and the maximum relative resistance changes (ΔR/R0) of 20 and 200 at 0.9 and 7.5% strains, respectively, were recorded in the nanocomposites (3 wt.-% MWCNTs) within the estimated volume resistivity range. A cyclic strain experiment shows the most stable and reproducible ΔR/R0 values in the 2%–5% strain range. The electrical conductivity and piezoresistivity of the investigated nanocomposites in correlation with the mechanical properties and observed morphology make them applicable for low-strain deformation-sensing.
- ItemClustering Semantic Predicates in the Open Research Knowledge Graph(Heidelberg : Springer, 2022) Arab Oghli, Omar; D’Souza, Jennifer; Auer, SörenWhen semantically describing knowledge graphs (KGs), users have to make a critical choice of a vocabulary (i.e. predicates and resources). The success of KG building is determined by the convergence of shared vocabularies so that meaning can be established. The typical lifecycle for a new KG construction can be defined as follows: nascent phases of graph construction experience terminology divergence, while later phases of graph construction experience terminology convergence and reuse. In this paper, we describe our approach tailoring two AI-based clustering algorithms for recommending predicates (in RDF statements) about resources in the Open Research Knowledge Graph (ORKG) https://orkg.org/. Such a service to recommend existing predicates to semantify new incoming data of scholarly publications is of paramount importance for fostering terminology convergence in the ORKG. Our experiments show very promising results: a high precision with relatively high recall in linear runtime performance. Furthermore, this work offers novel insights into the predicate groups that automatically accrue loosely as generic semantification patterns for semantification of scholarly knowledge spanning 44 research fields.
- ItemEasy Semantification of Bioassays(Heidelberg : Springer, 2022) Anteghini, Marco; D’Souza, Jennifer; dos Santos, Vitor A. P. Martins; Auer, SörenBiological data and knowledge bases increasingly rely on Semantic Web technologies and the use of knowledge graphs for data integration, retrieval and federated queries. We propose a solution for automatically semantifying biological assays. Our solution contrasts the problem of automated semantification as labeling versus clustering where the two methods are on opposite ends of the method complexity spectrum. Characteristically modeling our problem, we find the clustering solution significantly outperforms a deep neural network state-of-the-art labeling approach. This novel contribution is based on two factors: 1) a learning objective closely modeled after the data outperforms an alternative approach with sophisticated semantic modeling; 2) automatically semantifying biological assays achieves a high performance F1 of nearly 83%, which to our knowledge is the first reported standardized evaluation of the task offering a strong benchmark model.