Exploring the Design Space of Unsupervised Blocking with Pre-trained Language Models in Entity Resolution.
Chenchen SunYuyuan JinYang XuDerong ShenTiezheng NieXite WangPublished in: ADMA (1) (2023)
Keyphrases
- language model
- design space
- entity resolution
- pre trained
- record linkage
- probabilistic model
- information retrieval
- training data
- training examples
- design process
- n gram
- speech recognition
- supervised learning
- privacy preserving
- unsupervised learning
- control signals
- query processing
- design tools
- information extraction
- linked data
- semi supervised
- data integration
- link prediction
- markov networks
- search space
- conditional random fields
- unlabeled data
- labeled data
- case study
- active learning
- real world