5 results
Search Results
Now showing 1 - 5 of 5
- ItemDetecting Cross-Language Plagiarism using Open Knowledge Graphs(Aachen, Germany : RWTH Aachen, 2021) Stegmüller, Johannes; Bauer-Marquart, Fabian; Meuschke, Norman; Ruas, Terry; Schubotz, Moritz; Gipp, Bela; Zhang, Chengzhi; Mayr, Philipp; Lu, Wie; Zhang, YiIdentifying cross-language plagiarism is challenging, especially for distant language pairs and sense-for-sense translations. We introduce the new multilingual retrieval model Cross-Language Ontology-Based Similarity Analysis (CL-OSA) for this task. CL-OSA represents documents as entity vectors obtained from the open knowledge graph Wikidata. Opposed to other methods, CL-OSA does not require computationally expensive machine translation, nor pre-training using comparable or parallel corpora. It reliably disambiguates homonyms and scales to allow its application toWebscale document collections. We show that CL-OSA outperforms state-of-the-art methods for retrieving candidate documents from five large, topically diverse test corpora that include distant language pairs like Japanese-English. For identifying cross-language plagiarism at the character level, CL-OSA primarily improves the detection of sense-for-sense translations. For these challenging cases, CL-OSA’s performance in terms of the well-established PlagDet score exceeds that of the best competitor by more than factor two. The code and data of our study are openly available.
- ItemFalcon 2.0: An Entity and Relation Linking Tool over Wikidata(New York City, NY : Association for Computing Machinery, 2020) Sakor, Ahmad; Singh, Kuldeep; Patel, Anery; Vidal, Maria-EstherThe Natural Language Processing (NLP) community has significantly contributed to the solutions for entity and relation recognition from a natural language text, and possibly linking them to proper matches in Knowledge Graphs (KGs). Considering Wikidata as the background KG, there are still limited tools to link knowledge within the text to Wikidata. In this paper, we present Falcon 2.0, the first joint entity and relation linking tool over Wikidata. It receives a short natural language text in the English language and outputs a ranked list of entities and relations annotated with the proper candidates in Wikidata. The candidates are represented by their Internationalized Resource Identifier (IRI) in Wikidata. Falcon 2.0 resorts to the English language model for the recognition task (e.g., N-Gram tiling and N-Gram splitting), and then an optimization approach for the linking task. We have empirically studied the performance of Falcon 2.0 on Wikidata and concluded that it outperforms all the existing baselines. Falcon 2.0 is open source and can be reused by the community; all the required instructions of Falcon 2.0 are well-documented at our GitHub repository (https://github.com/SDM-TIB/falcon2.0). We also demonstrate an online API, which can be run without any technical expertise. Falcon 2.0 and its background knowledge bases are available as resources at https://labs.tib.eu/falcon/falcon2/.
- ItemMathematics in Wikidata(Aachen, Germany : RWTH Aachen, 2021) Scharpf, Philipp; Schubotz, Moritz; Gipp, Bela; Kaffee, Lucie-Aimée; Razniewski, Simon; Hogan, AidanDocuments from Science, Technology, Engineering, and Mathematics (STEM) disciplines usually contain a signicant amount of mathematical formulae alongside text. Some Mathematical Information Retrieval (MathIR) systems, e.g., Mathematical Question Answering (MathQA), exploit knowledge from Wikidata. Therefore, the mathematical information needs to be stored in items. In the last years, there have been efforts to define several properties and seed formulae together with their constituting identifiers into Wikidata. This paper summarizes the current state, challenges, and discussions related to this endeavor. Furthermore, some data mining methods (supervised formula annotation and concept retrieval) and applications (question answering and classification explainability) of the mathematical information are outlined. Finally, we discuss community feedback and issues related to integrating Mathematical Entity Linking (MathEL) into Wikidata and Wikipedia, which was rejected in 33% and 12% of the test cases, for Wikidata and Wikipedia respectively. Our long-term goal is to populate Wikidata, such that it can serve a variety of automated math reasoning tasks and AI systems.
- ItemBaroque AI(Zenodo, 2023) Worthington, Simon; Blümel, InaPublication prototype: A computational publishing and AI assisted writing course unit with students of the Open Knowledge class – at Hochschule Hannover with the Open Science Lab, TIB. The prototype publication exercise involves creating a fictional ‘exhibition catalogue’ drawing on Wikidata based cataloguing of seventeenth century painting deposited by the Bavarian State Painting Collections. The prototype demostrates how computational publishing can be used to bring together different distributed linked open data (LOD) sources. Additionally AI tools are used for assisted essay writing. Then both are encapsulated in a multi-format computational publication — allowing for asynchronous collaborative working. Distributed LOD sources include: Wikidata/base, Nextcloud, Thoth, Semantic Kompakkt, and TIB AV Portal. AI tools used for essay writing are — OpenAI and Perplexity. Eleven students completed the class unit which was carried out over March to April 2023. An open access OER guide to running the class, a template publication for use in the class are online on GitHub and designed for OER reuse. Full class information and resources are on Wikiversity. The open source software used is brought together in the ADA Pipeline.
- ItemDigital und partizipativ - Projekte in der Erinnerungskultur(Reutlingen : Berufsverband Information Bibliothek e. V., 2024) Fahrenkrog, Gabriele; Groh-Trautmann, LisaDie Erinnerungskultur an den Nationalsozialismus in Deutschland befindet sich im Umbruch. Doch wie kann eine lebendige Erinnerungskultur, die ein wichtige Grundlage für die Etablierung demokratischer Werte darstellt, gefördert werden? Die Digitalisierung und die Bereitstellung von offenen Daten eröffnen hierbei neue Wege. In Zusammenarbeit mit und gefördert durch verschiedene Stiftungen hat die TIB seit 2020 in mehreren Drittmittel-geförderten Projekten nach diesen neuen Wegen gesucht und Formen forschender Erinnerungsarbeit vor Ort erprobt. Anhand der TIB-Projekte “Orte des Gestapoterrors”, http://tib.eu/gestapo-terror-orte, “Remember Me!” rememberme-data.de und “WikiRemembrance” https://www.wikiremembrance.de/ soll exemplarisch aufgezeigt werden, wie Communities der Erinnerungskultur, Schülerinnen und Schüler aber auch andere Interessierte dazu befähigt werden können, selbst über den Umgang mit offenen Daten zu reflektieren, sie zu erzeugen, zu veröffentlichen und die Daten in neuen Kontexten zu verwenden. Zudem berichten wir, wie im Rahmen der Projekte in kollaborativen und partizipativen Arbeitsprozessen gemeinsam mit den Communities Daten der Öffentlichkeit zur Verfügung gestellt werden und welche Wege zur Vernetzung sich dafür als sinnvoll erwiesen haben. Im Verlauf der Projektarbeit hat sich gezeigt, dass sich unterschiedliche Zielgruppen, darunter Schülerinnen und Schüler, durch die Beschäftigung mit offenen Daten zu einem gemeinsamen forschenden Lernen über zeitgeschichtliche Themen vor Ort motivieren lassen und so erfahren, dass sie aktiv zu einer lebendigen Erinnerungskultur beitragen können. Die im Rahmen von “Orte des Gestapoterrors”, Remember Me! und “WikiRemembrance” erprobten digitalen Interaktionsformen lassen sich auch auf andere Projekte übertragen.