{ "types" : { "Bookmark" : { "pluralLabel" : "Bookmarks" }, "Publication" : { "pluralLabel" : "Publications" }, "GoldStandardPublication" : { "pluralLabel" : "GoldStandardPublications" }, "GoldStandardBookmark" : { "pluralLabel" : "GoldStandardBookmarks" }, "Tag" : { "pluralLabel" : "Tags" }, "User" : { "pluralLabel" : "Users" }, "Group" : { "pluralLabel" : "Groups" }, "Sphere" : { "pluralLabel" : "Spheres" } }, "properties" : { "count" : { "valueType" : "number" }, "date" : { "valueType" : "date" }, "changeDate" : { "valueType" : "date" }, "url" : { "valueType" : "url" }, "id" : { "valueType" : "url" }, "tags" : { "valueType" : "item" }, "user" : { "valueType" : "item" } }, "items" : [ { "type" : "Bookmark", "id" : "https://puma.ub.uni-stuttgart.de/url/476d5dfd675443a99607bfc2f959d093/diglezakis", "tags" : [ "forschungsdaten","metadata","technicalMetadata","tools","extraction" ], "intraHash" : "476d5dfd675443a99607bfc2f959d093", "label" : "File Information Tool Set (FITS)", "user" : "diglezakis", "description" : "Tool to extract technical metadata from Files", "date" : "2020-02-03 11:54:18", "changeDate" : "2020-11-06 08:45:56", "count" : 1, "url" : "https://projects.iq.harvard.edu/fits/home" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/27b0ff014a770fd41df75b72133a392d1/diglezakis", "tags" : [ "enrichment","NLP","forschungsdaten","metadata","ontologie","AI","catalysis","extraction" ], "intraHash" : "7b0ff014a770fd41df75b72133a392d1", "interHash" : "c9546ba455ebfbfdb3b0d76d7cfb9fef", "label" : "Generating knowledge graphs through text mining of catalysis research related literature", "user" : "diglezakis", "description" : "", "date" : "2025-09-16 09:26:11", "changeDate" : "2025-10-07 14:32:41", "count" : 3, "pub-type": "article", "journal": "Catal. Sci. Technol.","publisher":"The Royal Society of Chemistry", "year": "2024", "url": "http://dx.doi.org/10.1039/D4CY00369A", "author": [ "Alexander S. Behr","Diana Chernenko","Dominik Koßmann","Arjun Neyyathala","Schirin Hanf","Stephan A. Schunk","Norbert Kockmann" ], "authors": [ {"first" : "Alexander S.", "last" : "Behr"}, {"first" : "Diana", "last" : "Chernenko"}, {"first" : "Dominik", "last" : "Koßmann"}, {"first" : "Arjun", "last" : "Neyyathala"}, {"first" : "Schirin", "last" : "Hanf"}, {"first" : "Stephan A.", "last" : "Schunk"}, {"first" : "Norbert", "last" : "Kockmann"} ], "volume": "14","number": "19","pages": "5699-5713","abstract": "Structured research data management in catalysis is crucial, especially for large amounts of data, and should be guided by FAIR principles for easy access and compatibility of data. Ontologies help to organize knowledge in a structured and FAIR way. The increasing numbers of scientific publications call for automated methods to preselect and access the desired knowledge while minimizing the effort to search for relevant publications. While ontology learning can be used to create structured knowledge graphs, named entity recognition allows detection and categorization of important information in text. This work combines ontology learning and named entity recognition for automated extraction of key data from publications and organization of the implicit knowledge in a machine- and user-readable knowledge graph and data. CatalysisIE is a pre-trained model for such information extraction for catalysis research. This model is used and extended in this work based on a new data set, increasing the precision and recall of the model with regard to the data set. Validation of the presented workflow is presented on two datasets regarding catalysis research. Preformulated SPARQL-queries are provided to show the usability and applicability of the resulting knowledge graph for researchers.", "doi" : "10.1039/D4CY00369A", "bibtexKey": "D4CY00369A" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/277f729277f30bd002cebba436c384e90/diglezakis", "tags" : [ "schema","metadata","extraction","llm" ], "intraHash" : "77f729277f30bd002cebba436c384e90", "interHash" : "38d44e44ed8aa2a96c104197c3fbbc86", "label" : "LLMs4SchemaDiscovery: A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models", "user" : "diglezakis", "description" : "", "date" : "2025-07-12 11:07:19", "changeDate" : "2025-07-12 11:07:19", "count" : 1, "pub-type": "misc", "year": "2025", "url": "https://arxiv.org/abs/2504.00752", "author": [ "Sameer Sadruddin","Jennifer D'Souza","Eleni Poupaki","Alex Watkins","Hamed Babaei Giglou","Anisa Rula","Bora Karasulu","Sören Auer","Adrie Mackus","Erwin Kessels" ], "authors": [ {"first" : "Sameer", "last" : "Sadruddin"}, {"first" : "Jennifer", "last" : "D'Souza"}, {"first" : "Eleni", "last" : "Poupaki"}, {"first" : "Alex", "last" : "Watkins"}, {"first" : "Hamed Babaei", "last" : "Giglou"}, {"first" : "Anisa", "last" : "Rula"}, {"first" : "Bora", "last" : "Karasulu"}, {"first" : "Sören", "last" : "Auer"}, {"first" : "Adrie", "last" : "Mackus"}, {"first" : "Erwin", "last" : "Kessels"} ], "eprint" : "2504.00752", "archiveprefix" : "arXiv", "primaryclass" : "cs.CL", "bibtexKey": "sadruddin2025llms4schemadiscoveryhumanintheloopworkflowscientific" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/228cff38a293a8f2376e3488387b88297/diglezakis", "tags" : [ "metadata","engmeta","tools","extraction" ], "intraHash" : "28cff38a293a8f2376e3488387b88297", "interHash" : "b6eac40c2b6d9e29e99c8eece7d9e01b", "label" : "Like a rainbow in the dark: metadata annotation for HPC applications in the age of dark data", "user" : "diglezakis", "description" : "", "date" : "2024-12-05 15:34:23", "changeDate" : "2024-12-05 15:34:23", "count" : 4, "pub-type": "article", "journal": "The Journal of Supercomputing", "year": "2021", "url": "https://doi.org/10.1007/s11227-020-03602-6", "author": [ "Björn Schembera" ], "authors": [ {"first" : "Björn", "last" : "Schembera"} ], "volume": "77","number": "8","pages": "8946--8966","abstract": "The deluge of dark data is about to happen. Lacking data management capabilities, especially in the field of supercomputing, and missing data documentation (i.e., missing metadata annotation) constitute a major source of dark data. The present work contributes to addressing this challenge by presenting ExtractIng, a generic automated metadata extraction toolkit. Existing metadata information of simulation output files scattered through the file system, can be aggregated, parsed and converted to the EngMeta metadata model. Use cases from computational engineering are considered to demonstrate the viability of ExtractIng. The evaluation results show that the metadata extraction is simulation-code independent in the sense that it can handle data outputs from various fields of science, is easy to integrate into simulation workflows and compatible with a multitude of computational environments.", "issn" : "15730484", "refid" : "Schembera2021", "doi" : "10.1007/s11227-020-03602-6", "bibtexKey": "schembera2021rainbow" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2fe5c27bfa323a45b3c97de8f81f88da2/diglezakis", "tags" : [ "hpc-computing","metadata","crawler","NFDI4ING","extraction" ], "intraHash" : "fe5c27bfa323a45b3c97de8f81f88da2", "interHash" : "960db829af8e246ca25a1582ec3583a7", "label" : "A metadata crawler for simulation data management", "user" : "diglezakis", "description" : "", "date" : "2024-11-06 08:56:02", "changeDate" : "2024-11-06 08:56:02", "count" : 1, "pub-type": "misc", "year": "2021", "url": "https://gitlab.lrz.de/nfdi4ing/crawler", "author": [ "Christian Stemmer","Nils Hoppe","Benjamin Farnbacher","Ralev Radoslav","Giuseppe Chiapparino" ], "authors": [ {"first" : "Christian", "last" : "Stemmer"}, {"first" : "Nils", "last" : "Hoppe"}, {"first" : "Benjamin", "last" : "Farnbacher"}, {"first" : "Ralev", "last" : "Radoslav"}, {"first" : "Giuseppe", "last" : "Chiapparino"} ], "note": "[000][29*][000]","abstract": "HOMER (HPMC tool for Ontology-based Metadata Extraction and Re-use).", "urldate" : "2023-08-11", "bibtexKey": "stemmer_metadata_2021" } ] }