Stage-oe-small.jpg

Inproceedings3858: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
 
(Eine dazwischenliegende Version desselben Benutzers wird nicht angezeigt)
Zeile 13: Zeile 13:
 
|Booktitle=Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM'21)
 
|Booktitle=Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM'21)
 
|Publisher=ACM
 
|Publisher=ACM
 +
|Note=<br />Paper presentation on '''YouTube''': https://www.youtube.com/watch?v=Qb0zqn27veo
 
}}
 
}}
 
{{Publikation Details
 
{{Publikation Details
Zeile 33: Zeile 34:
 
|Forschungsgebiet=Wissensrepräsentation
 
|Forschungsgebiet=Wissensrepräsentation
 
}}
 
}}
Paper presentation on '''YouTube''': https://www.youtube.com/watch?v=Qb0zqn27veo
 

Aktuelle Version vom 11. Oktober 2021, 11:55 Uhr


Recommending Datasets for Scientific Problem Descriptions


Recommending Datasets for Scientific Problem Descriptions



Published: 2021

Buchtitel: Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM'21)
Verlag: ACM

Referierte VeröffentlichungNote:
Paper presentation on YouTube: https://www.youtube.com/watch?v=Qb0zqn27veo

BibTeX

Kurzfassung
The steadily rising number of datasets is making it increasingly difficult for researchers and practitioners to be aware of all datasets, particularly of the most relevant datasets for a given research problem. To this end, dataset search engines have been proposed. However, they are based on user’s keywords and, thus, have difficulty determining precisely fitting datasets for complex research problems. In this paper, we propose a system that recommends suitable datasets based on a given research problem description. The recommendation task is designed as a domain-specific text classification task. As shown in a comprehensive offline evaluation using various state-of-the-art models, as well as 88,000 paper abstracts and 265,000 citation contexts as research problem descriptions, we obtain an F1-score of 0.75. In an additional user study, we show that users in real-world settings are 88% satisfied in all test cases. We therefore see promising future directions for dataset recommendation.

Download: Media:DataRec_CIKM2021.pdf
Weitere Informationen unter: Link
DOI Link: 10.1145/3459637.3482166



Forschungsgruppe

Web Science


Forschungsgebiet

Wissensrepräsentation, Maschinelles Lernen, Natürliche Sprachverarbeitung, Künstliche Intelligenz