Database Entity Recognition with Data Augmentation and Deep Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916920472633344 |
|---|---|
| author | Fu, Zikun Yang, Chen Davoudi, Kourosh Pu, Ken Q. |
| author_facet | Fu, Zikun Yang, Chen Davoudi, Kourosh Pu, Ken Q. |
| contents | This paper addresses the challenge of Database Entity Recognition (DB-ER) in Natural Language Queries (NLQ). We present several key contributions to advance this field: (1) a human-annotated benchmark for DB-ER task, derived from popular text-to-sql benchmarks, (2) a novel data augmentation procedure that leverages automatic annotation of NLQs based on the corresponding SQL queries which are available in popular text-to-SQL benchmarks, (3) a specialized language model based entity recognition model using T5 as a backbone and two down-stream DB-ER tasks: sequence tagging and token classification for fine-tuning of backend and performing DB-ER respectively. We compared our DB-ER tagger with two state-of-the-art NER taggers, and observed better performance in both precision and recall for our model. The ablation evaluation shows that data augmentation boosts precision and recall by over 10%, while fine-tuning of the T5 backbone boosts these metrics by 5-10%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19372 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Database Entity Recognition with Data Augmentation and Deep Learning Fu, Zikun Yang, Chen Davoudi, Kourosh Pu, Ken Q. Computation and Language Artificial Intelligence Databases Machine Learning This paper addresses the challenge of Database Entity Recognition (DB-ER) in Natural Language Queries (NLQ). We present several key contributions to advance this field: (1) a human-annotated benchmark for DB-ER task, derived from popular text-to-sql benchmarks, (2) a novel data augmentation procedure that leverages automatic annotation of NLQs based on the corresponding SQL queries which are available in popular text-to-SQL benchmarks, (3) a specialized language model based entity recognition model using T5 as a backbone and two down-stream DB-ER tasks: sequence tagging and token classification for fine-tuning of backend and performing DB-ER respectively. We compared our DB-ER tagger with two state-of-the-art NER taggers, and observed better performance in both precision and recall for our model. The ablation evaluation shows that data augmentation boosts precision and recall by over 10%, while fine-tuning of the T5 backbone boosts these metrics by 5-10%. |
| title | Database Entity Recognition with Data Augmentation and Deep Learning |
| topic | Computation and Language Artificial Intelligence Databases Machine Learning |
| url | https://arxiv.org/abs/2508.19372 |