Towards Universal Dense Blocking for Entity Resolution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914769803411456 |
|---|---|
| author | Wang, Tianshu Lin, Hongyu Han, Xianpei Chen, Xiaoyang Cao, Boxi Sun, Le |
| author_facet | Wang, Tianshu Lin, Hongyu Han, Xianpei Chen, Xiaoyang Cao, Boxi Sun, Le |
| contents | Blocking is a critical step in entity resolution, and the emergence of neural network-based representation models has led to the development of dense blocking as a promising approach for exploring deep semantics in blocking. However, previous advanced self-supervised dense blocking approaches require domain-specific training on the target domain, which limits the benefits and rapid adaptation of these methods. To address this issue, we propose UniBlocker, a dense blocker that is pre-trained on a domain-independent, easily-obtainable tabular corpus using self-supervised contrastive learning. By conducting domain-independent pre-training, UniBlocker can be adapted to various downstream blocking scenarios without requiring domain-specific fine-tuning. To evaluate the universality of our entity blocker, we also construct a new benchmark covering a wide range of blocking tasks from multiple domains and scenarios. Our experiments show that the proposed UniBlocker, without any domain-specific learning, significantly outperforms previous self- and unsupervised dense blocking methods and is comparable and complementary to the state-of-the-art sparse blocking methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_14831 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Universal Dense Blocking for Entity Resolution Wang, Tianshu Lin, Hongyu Han, Xianpei Chen, Xiaoyang Cao, Boxi Sun, Le Databases Computation and Language Information Retrieval Blocking is a critical step in entity resolution, and the emergence of neural network-based representation models has led to the development of dense blocking as a promising approach for exploring deep semantics in blocking. However, previous advanced self-supervised dense blocking approaches require domain-specific training on the target domain, which limits the benefits and rapid adaptation of these methods. To address this issue, we propose UniBlocker, a dense blocker that is pre-trained on a domain-independent, easily-obtainable tabular corpus using self-supervised contrastive learning. By conducting domain-independent pre-training, UniBlocker can be adapted to various downstream blocking scenarios without requiring domain-specific fine-tuning. To evaluate the universality of our entity blocker, we also construct a new benchmark covering a wide range of blocking tasks from multiple domains and scenarios. Our experiments show that the proposed UniBlocker, without any domain-specific learning, significantly outperforms previous self- and unsupervised dense blocking methods and is comparable and complementary to the state-of-the-art sparse blocking methods. |
| title | Towards Universal Dense Blocking for Entity Resolution |
| topic | Databases Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2404.14831 |