Hrou, Moussab: Evaluating SQuAD-based Question Answering for the Open Research Knowledge Graph Completion. Hannover : Gottfried Wilhelm Leibniz Universität Hannover, Bachelor Thesis, 2022, IX, 48 S. DOI: https://doi.org/10.15488/12854
Zusammenfassung: | |
Every year, approximately around 2.5 million new scientific papers are published.With the rapidly growing publication trends, it is increasingly difficult to manuallysort through and keep track of the relevant research – a problem that is only moreacute in a multidisciplinary setting. The Open Research Knowledge Graph (ORKG)is a next-generation scholarly communication platform that aims to address thisissue by making knowledge about scholarly contributions machine-actionable, thusenabling completely new ways of human-machine assistance in comprehending re-search progress.As such, the ORKG is powered by a diverse spectrum of NLP services to assist theexpert users in structuring scholarly contributions and searching for the most rele-vant contributions. For a prospective recommendation service, this thesis examinesthe task of automated ORKG completion as an object extraction task from a givenpaper Abstract for a query ORKG predicate. As a main contribution of this thesis,automated ORKG completion is formulated as an extractive Question Answering(QA) machine learning objective under an open world assumption. Specifically, thetask attempted in this work is fixed-prompt Language Model (LM) tuning (LMT)for few-shot ORKG object prediction formulated as the well-known SQuAD extrac-tive QA objective. Three variants of BERT-based transfomer LMs are evaluated.To support the novel LMT task, this thesis introduces a scholarly QA dataset akinin characteristics to the SQuAD QA dataset generated semi-automatically from theORKG knowledge base. As a result, the BERT model variants when tested in vanilla setting versus after LMT, show a positive, significant performance uplift for auto-mated ORKG completion as an object completion task. This thesis offers a strong empirical basis for future research aiming at a production-ready automated ORKG completion model. | |
Lizenzbestimmungen: | CC BY 3.0 DE |
Publikationstyp: | BachelorThesis |
Publikationsstatus: | publishedVersion |
Erstveröffentlichung: | 2022 |
Die Publikation erscheint in Sammlung(en): | Fakultät für Elektrotechnik und Informatik |
Pos. | Land | Downloads | ||
---|---|---|---|---|
Anzahl | Proz. | |||
1 | ![]() |
Germany | 229 | 35,73% |
2 | ![]() |
United States | 117 | 18,25% |
3 | ![]() |
No geo information available | 56 | 8,74% |
4 | ![]() |
India | 34 | 5,30% |
5 | ![]() |
United Kingdom | 22 | 3,43% |
6 | ![]() |
Pakistan | 16 | 2,50% |
7 | ![]() |
Iran, Islamic Republic of | 12 | 1,87% |
8 | ![]() |
Korea, Republic of | 11 | 1,72% |
9 | ![]() |
China | 9 | 1,40% |
10 | ![]() |
Canada | 9 | 1,40% |
andere | 126 | 19,66% |
Hinweis
Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.