Abstract
Neural table-to-text generation models have achieved remarkable progress on an array of tasks. However, due to the data-hungry nature of neural models, their performances strongly rely on large-scale training examples, limiting their applicability in real-world applications. To address this, we propose a new framework: Prototype-to-Generate (P2G), for table-to-text generation under the few-shot scenario. The proposed framework utilizes the retrieved prototypes, which are jointly selected by an IR system and a novel prototype selector to help the model bridging the structural gap between tables and texts. Experimental results on three benchmark datasets with three state-of-the-art models demonstrate that the proposed framework significantly improves the model performance across various evaluation metrics.- Anthology ID:
- 2021.findings-emnlp.77
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 910–917
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.77
- DOI:
- 10.18653/v1/2021.findings-emnlp.77
- Cite (ACL):
- Yixuan Su, Zaiqiao Meng, Simon Baker, and Nigel Collier. 2021. Few-Shot Table-to-Text Generation with Prototype Memory. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 910–917, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Few-Shot Table-to-Text Generation with Prototype Memory (Su et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.findings-emnlp.77.pdf
- Code
- yxuansu/few-shot-table-to-text-generation