Knowledge Transfer for Entity Resolution with Siamese Neural Networks

Loster, Michael; Koumarelas, Ioannis; Naumann, Felix

doi:10.1145/3410157

“…Our framework is matcher-agnostic: it can support any kind of matching function, such as a DNF of similarity join predicates on multiple attributes [18,20], a human judging the pairs of records on a crowdsourcing platform [17], an unsupervised matcher based on generative models [44], or a complex deep learning model exploiting pre-trained language models [22] or transfer learning [23]. Our framework allows indicating the matching function for a particular ER task within an SQL query denoted by 𝜇 𝑄 .…”

Section: Matching Functionmentioning

confidence: 99%

Entity resolution on-demand

Simonini

¹

,

Zecchini

²

,

Bergamaschi

³

et al. 2022

Self Cite

View full text Add to dashboard Cite

Entity Resolution (ER) aims to identify and merge records that refer to the same real-world entity. ER is typically employed as an expensive cleaning step on the entire data before consuming it. Yet, determining which entities are useful once cleaned depends solely on the user's application, which may need only a fraction of them. For instance, when dealing with Web data, we would like to be able to filter the entities of interest gathered from multiple sources without cleaning the entire, continuously-growing data. Similarly, when querying data lakes, we want to transform data on-demand and return the results in a timely manner---a fundamental requirement of ELT ( Extract-Load-Transform ) pipelines. We propose BrewER , a framework to evaluate SQL SP queries on dirty data while progressively returning results as if they were issued on cleaned data. BrewER tries to focus the cleaning effort on one entity at a time, following an ORDER BY predicate. Thus, it inherently supports top-k and stop-and-resume execution. For a wide range of applications, a significant amount of resources can be saved. We exhaustively evaluate and show the efficacy of BrewER on four real-world datasets.

show abstract

“…Existing explorations seek solution from leveraging external data to improving annotation efficiency. External data can be aggregated via transfer learning (Zhao and He, 2019;Kasai et al, 2019;Loster et al, 2021), or via pre-training language models . For better annotations, researchers tried active learning (Kasai et al, 2019;Nafa et al, 2020;Sarawagi and Bhamidipaty, 2002;Arasu et al, 2010), or crowd sourcing techniques (Wang et al, 2012;Gokhale et al, 2014).…”

Section: Related Workmentioning

confidence: 99%

“…Supervised deep learning EM relies on large amounts of labeled training data, which is extremely costly in reality. Attempts have been made to leverage external data via transfer learning (Zhao and He, 2019;Kasai et al, 2019;Loster et al, 2021) and pre-trained language model based methods . Other attempts have also been made to improve labeling efficiency via active learning (Nafa et al, 2020) and crowdsourcing techniques (Gokhale et al, 2014;Wang et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making

Yao¹,

Li²,

Dong³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Entity Matching (EM) aims at recognizing entity records that denote the same real-world object. Neural EM models learn vector representation of entity descriptions and match entities end-to-end. Though robust, these methods require many annotated resources for training, and lack of interpretability. In this paper, we propose a novel EM framework that consists of Heterogeneous Information Fusion (HIF) and Key Attribute Tree (KAT) Induction to decouple feature representation from matching decision. Using self-supervised learning and mask mechanism in pre-trained language modeling, HIF learns the embeddings of noisy attribute values by inter-attribute attention with unlabeled data. Using a set of comparison features and a limited amount of annotated data, KAT Induction learns an efficient decision tree that can be interpreted by generating entity matching rules whose structure is advocated by domain experts. Experiments on 6 public datasets and 3 industrial datasets show that our method is highly efficient and outperforms SOTA EM models in most cases. Our codes and datasets can be obtained from https:// github.com/THU-KEG/HIF-KAT.

show abstract

“…Existing explorations seek solution from leveraging external data to improving annotation efficiency. External data can be aggregated via transfer learning (Zhao and He, 2019;Kasai et al, 2019;Loster et al, 2021), or via pre-training language models . For better annotations, researchers tried active learning (Kasai et al, 2019;Nafa et al, 2020;Sarawagi and Bhamidipaty, 2002;Arasu et al, 2010), or crowd sourcing techniques (Wang et al, 2012;Gokhale et al, 2014).…”

Section: Related Workmentioning

confidence: 99%

“…Supervised deep learning EM relies on large amounts of labeled training data, which is extremely costly in reality. Attempts have been made to leverage external data via transfer learning (Zhao and He, 2019;Kasai et al, 2019;Loster et al, 2021) and pre-trained language model based methods . Other attempts have also been made to improve labeling efficiency via active learning (Nafa et al, 2020) and crowdsourcing techniques (Gokhale et al, 2014;Wang et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making

Yao

¹

,

Li

²

,

Dong

³

et al. 2021

Preprint

0

View full text Add to dashboard Cite

Entity Matching (EM) aims at recognizing entity records that denote the same real-world object. Neural EM models learn vector representation of entity descriptions and match entities end-to-end. Though robust, these methods require many annotated resources for training, and lack of interpretability. In this paper, we propose a novel EM framework that consists of Heterogeneous Information Fusion (HIF) and Key Attribute Tree (KAT) Induction to decouple feature representation from matching decision. Using self-supervised learning and mask mechanism in pre-trained language modeling, HIF learns the embeddings of noisy attribute values by inter-attribute attention with unlabeled data. Using a set of comparison features and a limited amount of annotated data, KAT Induction learns an efficient decision tree that can be interpreted by generating entity matching rules whose structure is advocated by domain experts. Experiments on 6 public datasets and 3 industrial datasets show that our method is highly efficient and outperforms SOTA EM models in most cases. Our codes and datasets can be obtained from https:// github.com/THU-KEG/HIF-KAT.

show abstract

Knowledge Transfer for Entity Resolution with Siamese Neural Networks

Cited by 13 publications

References 38 publications

Entity resolution on-demand

Entity resolution on-demand

Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making

Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making

Contact Info

Product

Resources

About