EUVIMEDEUVIMED entdecken
Crossref

Pre-Trained Embeddings for Entity Resolution: An Experimental Analysis

Alexandros Zeakis, George Papadakis, Dimitrios Skoutas, Manolis Koubarakis

Proceedings of the VLDB Endowment · 2023-05 · 16 (9) · 2225-2238

DOI: 10.14778/3598581.3598594 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 10.07.2023. Verfasst von Alexandros Zeakis und 3 weiteren Autor:innen. Die Arbeit wurde bisher 61-mal zitiert (Crossref) und nennt 67 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Many recent works on Entity Resolution (ER) leverage Deep Learning techniques involving language models to improve effectiveness. This is applied to both main steps of ER, i.e., blocking and matching. Several pre-trained embeddings have been tested, with the most popular ones being fastText and variants of the BERT model. However, there is no detailed analysis of their pros and cons. To cover this gap, we perform a thorough experimental analysis of 12 popular language models over 17 established benchmark datasets. First, we assess their vectorization overhead for converting all input entities into dense embeddings vectors. Second, we investigate their blocking performance, performing a detailed scalability analysis, and comparing them with the state-of-the-art deep learning-based blocking method. Third, we conclude with their relative performance for both supervised and unsupervised matching. Our experimental results provide novel insights into the strengths and weaknesses of the main language models, facilitating researchers and practitioners to select the most suitable ones in practice.

Zitieren

APA

Zeakis, A., Papadakis, G., Skoutas, D., & Koubarakis, M. (2023). Pre-Trained Embeddings for Entity Resolution: An Experimental Analysis. Proceedings of the VLDB Endowment, 16(9), 2225-2238. https://doi.org/10.14778/3598581.3598594

Vancouver

Zeakis A, Papadakis G, Skoutas D, Koubarakis M. Pre-Trained Embeddings for Entity Resolution: An Experimental Analysis. Proceedings of the VLDB Endowment. 2023;16(9):2225-2238. doi:10.14778/3598581.3598594

BibTeX
@article{Zeakis2023,
  author = {Zeakis, Alexandros and Papadakis, George and Skoutas, Dimitrios and Koubarakis, Manolis},
  title = {Pre-Trained Embeddings for Entity Resolution: An Experimental Analysis},
  journal = {Proceedings of the VLDB Endowment},
  year = {2023},
  volume = {16},
  number = {9},
  pages = {2225--2238},
  doi = {10.14778/3598581.3598594}
}
Kostenlos starten →