Deep entity matching with pre-trained language models

By Yuliang Li, Yoshihiko Suhara, AnHai Doan, Wang Chiew Tan. Proceedings of the VLDB Endowment, 2020

516 citations recorded by the source corpus.

We present Ditto, a novel entity matching system based on pre-trained Transformer-based language models. We fine-tune and cast EM as a sequence-pair classification problem to leverage such models with a simple architecture. Our experiments show that a straight-forward application of language models such as BERT, DistilBERT, or RoBERTa pre-trained on large text corpora already significantly improves the matching quality and outperforms previous state-of-the-art (SOTA), by up to 29% of F1 score on benchmark datasets. We also developed three optimization techniques to further improve Ditto's matching capability. Ditto allows domain knowledge to be injected by highlighting important pieces of input information that may be of interest when making matching decisions. Ditto also summarizes strings that are too long so that only the essential information is retained and used for EM. Finally, Ditto adapts a SOTA technique on data augmentation for text to EM to augment the training data with (difficult) examples. This way, Ditto is forced to learn "harder" to improve the model's matching capability. The optimizations we developed further boost the performance of Ditto by up to 9.8%. Perhaps more surprisingly, we establish that Ditto can achieve the previous SOTA results with at most half the number of labeled data. Finally, we demonstrate Ditto's effectiveness on a real-world large-scale EM task. On matching two company datasets consisting of 789K and 412K records, Ditto achieves a high F1 score of 96.5%.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/512f34906ddaefe885af2e5eec9b2b3b50ffd377

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

Knowledge Graphs 2021: A Data Odyssey (2021, methodology): “In fact, similar approaches have lately been leveraged for DB problems, like QA over DB tables [13, 36], QA over web tables and text [40], or entity matching for data integration [1, 16].”
TabLLM: Few-shot Classification of Tabular Data with Large Language Models (2022, background): “Li et al. (2020) investigate the ability of language models to perform entity matching on tabular data, i.e. determining if two rows refer to the same object.”
On the Gap between Adoption and Understanding in NLP (2021, methodology): “…organized and easy-to-use source code 3 that made it possible to use the models as a baseline or as the foundation of many other research works (Li et al., 2020; Ke et al., 2020; Zemlyanskiy et al., 2021; Bianchi et al., 2021c,b, inter alia), suggesting that this kind of release can be of…”
Can Foundation Models Wrangle Your Data? (2022, methodology): “Recently, methods relying on PLMs [46] have become SoTA for this task.”