From Retrieval to Generation: Efficient and Effective Entity Set Expansion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910553157402624 |
|---|---|
| author | Huang, Shulin Ma, Shirong Li, Yangning Li, Yinghui Zheng, Hai-Tao |
| author_facet | Huang, Shulin Ma, Shirong Li, Yangning Li, Yinghui Zheng, Hai-Tao |
| contents | Entity Set Expansion (ESE) is a critical task aiming at expanding entities of the target semantic class described by seed entities. Most existing ESE methods are retrieval-based frameworks that need to extract contextual features of entities and calculate the similarity between seed entities and candidate entities. To achieve the two purposes, they iteratively traverse the corpus and the entity vocabulary, resulting in poor efficiency and scalability. Experimental results indicate that the time consumed by the retrieval-based ESE methods increases linearly with entity vocabulary and corpus size. In this paper, we firstly propose Generative Entity Set Expansion (GenExpan) framework, which utilizes a generative pre-trained auto-regressive language model to accomplish ESE task. Specifically, a prefix tree is employed to guarantee the validity of entity generation, and automatically generated class names are adopted to guide the model to generate target entities. Moreover, we propose Knowledge Calibration and Generative Ranking to further bridge the gap between generic knowledge of the language model and the goal of ESE task. For efficiency, expansion time consumed by GenExpan is independent of entity vocabulary and corpus size, and GenExpan achieves an average 600% speedup compared to strong baselines. For expansion effectiveness, our framework outperforms previous state-of-the-art ESE methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_03531 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | From Retrieval to Generation: Efficient and Effective Entity Set Expansion Huang, Shulin Ma, Shirong Li, Yangning Li, Yinghui Zheng, Hai-Tao Computation and Language Information Retrieval Entity Set Expansion (ESE) is a critical task aiming at expanding entities of the target semantic class described by seed entities. Most existing ESE methods are retrieval-based frameworks that need to extract contextual features of entities and calculate the similarity between seed entities and candidate entities. To achieve the two purposes, they iteratively traverse the corpus and the entity vocabulary, resulting in poor efficiency and scalability. Experimental results indicate that the time consumed by the retrieval-based ESE methods increases linearly with entity vocabulary and corpus size. In this paper, we firstly propose Generative Entity Set Expansion (GenExpan) framework, which utilizes a generative pre-trained auto-regressive language model to accomplish ESE task. Specifically, a prefix tree is employed to guarantee the validity of entity generation, and automatically generated class names are adopted to guide the model to generate target entities. Moreover, we propose Knowledge Calibration and Generative Ranking to further bridge the gap between generic knowledge of the language model and the goal of ESE task. For efficiency, expansion time consumed by GenExpan is independent of entity vocabulary and corpus size, and GenExpan achieves an average 600% speedup compared to strong baselines. For expansion effectiveness, our framework outperforms previous state-of-the-art ESE methods. |
| title | From Retrieval to Generation: Efficient and Effective Entity Set Expansion |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2304.03531 |