State-of-the-art Entity Matching (EM) approaches rely on transformer architectures, such as BERT, for generating highly contextualized embeddings of terms. The embeddings are then used to predict whether pairs of entity descriptions refer to the same real-world entity. BERT-based EM models demonstrated to be effective, but act as black-boxes for the users, who have limited insight into the motivations behind their decisions. In this paper, we perform a multi-facet analysis of the components of pre-trained and fine-tuned BERT architectures applied to an EM task. The main findings resulting from our extensive experimental evaluation are (1) the fine-tuning process applied to the EM task mainly modifies the last layers of the BERT components, but in a different way on tokens belonging to descriptions of matching / non-matching entities; (2) the special structure of the EM datasets, where records are pairs of entity descriptions is recognized by BERT; (3) the pair-wise semantic similarity of tokens is not a key knowledge exploited by BERT-based EM models.
Analyzing How BERT Performs Entity Matching / Paganelli, M.; Del Buono, F.; Baraldi, A.; Guerra, F.. - In: PROCEEDINGS OF THE VLDB ENDOWMENT. - ISSN 2150-8097. - 15:8(2022), pp. 1726-1738. (Intervento presentato al convegno 48th International Conference on Very Large Data Bases, VLDB 2022 tenutosi a aus nel 2022) [10.14778/3529337.3529356].
Analyzing How BERT Performs Entity Matching
Paganelli M.;Del Buono F.;Baraldi A.;Guerra F.
2022
Abstract
State-of-the-art Entity Matching (EM) approaches rely on transformer architectures, such as BERT, for generating highly contextualized embeddings of terms. The embeddings are then used to predict whether pairs of entity descriptions refer to the same real-world entity. BERT-based EM models demonstrated to be effective, but act as black-boxes for the users, who have limited insight into the motivations behind their decisions. In this paper, we perform a multi-facet analysis of the components of pre-trained and fine-tuned BERT architectures applied to an EM task. The main findings resulting from our extensive experimental evaluation are (1) the fine-tuning process applied to the EM task mainly modifies the last layers of the BERT components, but in a different way on tokens belonging to descriptions of matching / non-matching entities; (2) the special structure of the EM datasets, where records are pairs of entity descriptions is recognized by BERT; (3) the pair-wise semantic similarity of tokens is not a key knowledge exploited by BERT-based EM models.File | Dimensione | Formato | |
---|---|---|---|
p1726-paganelli.pdf
Open access
Tipologia:
Versione pubblicata dall'editore
Dimensione
3.08 MB
Formato
Adobe PDF
|
3.08 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris