Deep Indexed Active Learning for Matching Heterogeneous Entity Representations
arXiv:2104.03986 · doi:10.14778/3485450.3485455
Abstract
Given two large lists of records, the task in entity resolution (ER) is to find the pairs from the Cartesian product of the lists that correspond to the same real world entity. Typically, passive learning methods on such tasks require large amounts of labeled data to yield useful models. Active Learning is a promising approach for ER in low resource settings. However, the search space, to find informative samples for the user to label, grows quadratically for instance-pair tasks making active learning hard to scale. Previous works, in this setting, rely on hand-crafted predicates, pre-trained language model embeddings, or rule learning to prune away unlikely pairs from the Cartesian product. This blocking step can miss out on important regions in the product space leading to low recall. We propose DIAL, a scalable active learning approach that jointly learns embeddings to maximize recall for blocking and accuracy for matching blocked pairs. DIAL uses an Index-By-Committee framework, where each committee member learns representations based on powerful pre-trained transformer language models. We highlight surprising differences between the matcher and the blocker in the creation of the training data and the objective used to train their parameters. Experiments on five benchmark datasets and a multilingual record matching dataset show the effectiveness of our approach in terms of precision, recall and running time. Code is available at https://github.com/ArjitJ/DIAL
arXiv commentVLDB 2022
References in corpus (15)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Decoupled Weight Decay Regularization
- Active Learning for Convolutional Neural Networks: A Core-Set Approach
- Deep Bayesian Active Learning with Image Data
- Deep Entity Matching with Pre-Trained Language Models
- BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
- Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
- DeepER -- Deep Entity Resolution
- Neural Networks for Entity Matching: A Survey
- Diverse mini-batch Active Learning
- A Comprehensive Benchmark Framework for Active Learning Methods in Entity Matching
- AutoBlock: A Hands-off Blocking Framework for Entity Matching
- A Survey of Deep Active Learning
- Efficient and Effective ER with Progressive Blocking
- CorDEL: A Contrastive Deep Learning Approach for Entity Linkage