LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control
Yilun Zhao, Zhenting Qi, Linyong Nan, Lorenzo Jaime Flores, Dragomir Radev
Abstract
Logical Table-to-Text (LT2T) generation is tasked with generating logically faithful sentences from tables. There currently exists two challenges in the field: 1) Faithfulness: how to generate sentences that are factually correct given the table content; 2) Diversity: how to generate multiple sentences that offer different perspectives on the table. This work proposes LoFT, which utilizes logic forms as fact verifiers and content planners to control LT2T generation. Experimental results on the LogicNLG dataset demonstrate that LoFT is the first model that addresses unfaithfulness and lack of diversity issues simultaneously. Our code is publicly available at https://github.com/Yale-LILY/LoFT.- Anthology ID:
- 2023.eacl-main.40
- Volume:
- Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 554–561
- Language:
- URL:
- https://aclanthology.org/2023.eacl-main.40
- DOI:
- 10.18653/v1/2023.eacl-main.40
- Cite (ACL):
- Yilun Zhao, Zhenting Qi, Linyong Nan, Lorenzo Jaime Flores, and Dragomir Radev. 2023. LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 554–561, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control (Zhao et al., EACL 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.eacl-main.40.pdf