Abstract
We consider the task of data-to-text generation, which aims to create textual output from non-linguistic input. We focus on generating long-form text, that is, documents with multiple paragraphs, and propose a neural model enhanced with a planning component responsible for organizing high-level information in a coherent and meaningful way. We infer latent plans sequentially with a structured variational model, while interleaving the steps of planning and generation. Text is generated by conditioning on previous variational decisions and previously generated text. Experiments on two data-to-text benchmarks (RotoWire and MLB) show that our model outperforms strong baselines and is sample-efficient in the face of limited training data (e.g., a few hundred instances).- Anthology ID:
- 2022.tacl-1.40
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 10
- Month:
- Year:
- 2022
- Address:
- Cambridge, MA
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 697–715
- Language:
- URL:
- https://aclanthology.org/2022.tacl-1.40
- DOI:
- 10.1162/tacl_a_00484
- Cite (ACL):
- Ratish Puduppully, Yao Fu, and Mirella Lapata. 2022. Data-to-text Generation with Variational Sequential Planning. Transactions of the Association for Computational Linguistics, 10:697–715.
- Cite (Informal):
- Data-to-text Generation with Variational Sequential Planning (Puduppully et al., TACL 2022)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2022.tacl-1.40.pdf