dc.identifier.uri |
http://dx.doi.org/10.15488/17475 |
|
dc.identifier.uri |
https://www.repo.uni-hannover.de/handle/123456789/17605 |
|
dc.contributor.author |
D’Souza, Jennifer
|
|
dc.contributor.author |
Hrou, Moussab
|
|
dc.contributor.author |
Auer, Sören
|
|
dc.contributor.editor |
Strauss, Christine
|
|
dc.contributor.editor |
Amagasa, Toshiyuki
|
|
dc.contributor.editor |
Kotsis, Gabriele
|
|
dc.contributor.editor |
Tjoa, A Min
|
|
dc.contributor.editor |
Khalil, Ismail
|
|
dc.date.accessioned |
2024-06-04T07:19:45Z |
|
dc.date.available |
2024-06-04T07:19:45Z |
|
dc.date.issued |
2023 |
|
dc.identifier.citation |
D’Souza, J.; Hrou, M.; Auer, S.: Evaluating Prompt-Based Question Answering for Object Prediction in the Open Research Knowledge Graph. In: Strauss, C.; Amagasa, T.; Kotsis, G.; Tjoa, A M.; Khalil, I. (Eds.): Database and Expert Systems Applications: 34th International Conference, DEXA 2023, Penang, Malaysia, August 28–30, 2023, Proceedings, Part I. New York, NY : Springer, 2023 (Lecture Notes in Computer Science ; 14146), S. 508-515. DOI: https://doi.org/10.1007/978-3-031-39847-6_40 |
|
dc.description.abstract |
Recent investigations have explored prompt-based training of transformer language models for new text genres in low-resource settings. This approach has proven effective in transferring pre-trained or fine-tuned models to resource-scarce environments. This work presents the first results on applying prompt-based training to transformers for scholarly knowledge graph object prediction. Methodologically, it stands out in two main ways: 1) it deviates from previous studies that propose entity and relation extraction pipelines, and 2) it tests the method in a significantly different domain, scholarly knowledge, evaluating linguistic, probabilistic, and factual generalizability of large-scale transformer models. Our findings demonstrate that: i) out-of-the-box transformer models underperform on the new scholarly domain, ii) prompt-based training improves performance by up to 40% in relaxed evaluation, and iii) tests of the models in a distinct domain reveals a gap in capturing domain knowledge, highlighting the need for increased attention and resources in the scholarly domain for transformer models. |
eng |
dc.language.iso |
eng |
|
dc.publisher |
New York, NY : Springer |
|
dc.relation.ispartof |
Database and Expert Systems Applications: 34th International Conference, DEXA 2023, Penang, Malaysia, August 28–30, 2023, Proceedings, Part I |
|
dc.relation.ispartofseries |
Lecture Notes in Computer Science ; 14146 |
|
dc.rights |
This document may be downloaded, read, stored and printed for your own use within the limits of § 53 UrhG but it may not be distributed on other websites via the internet or passed on to external parties. |
eng |
dc.rights |
Dieses Dokument darf im Rahmen von § 53 UrhG zum eigenen Gebrauch kostenfrei heruntergeladen, gelesen, gespeichert und ausgedruckt, aber nicht auf anderen Webseiten im Internet bereitgestellt oder an Außenstehende weitergegeben werden. |
ger |
dc.subject |
Knowledge Graph Completion |
eng |
dc.subject |
Natural Language Processing |
eng |
dc.subject |
Open Research Knowledge Graph |
eng |
dc.subject |
Prompt-based Question Answering |
eng |
dc.subject |
Question Answering |
eng |
dc.subject.classification |
Konferenzschrift |
ger |
dc.subject.ddc |
620 | Ingenieurwissenschaften und Maschinenbau
|
|
dc.title |
Evaluating Prompt-Based Question Answering for Object Prediction in the Open Research Knowledge Graph |
eng |
dc.type |
BookPart |
|
dc.type |
Text |
|
dc.relation.essn |
1611-3349 |
|
dc.relation.isbn |
978-3-031-39847-6 |
|
dc.relation.issn |
0302-9743 |
|
dc.relation.doi |
https://doi.org/10.1007/978-3-031-39847-6_40 |
|
dc.bibliographicCitation.volume |
14146 |
|
dc.bibliographicCitation.firstPage |
508 |
|
dc.bibliographicCitation.lastPage |
515 |
|
dc.description.version |
publishedVersion |
eng |
tib.accessRights |
frei zug�nglich |
|