Abstract
We present a novel approach to data-to-text generation based on iterative text editing. Our approach maximizes the completeness and semantic accuracy of the output text while leveraging the abilities of recent pre-trained models for text editing (LaserTagger) and language modeling (GPT-2) to improve the text fluency. To this end, we first transform data items to text using trivial templates, and then we iteratively improve the resulting text by a neural model trained for the sentence fusion task. The output of the model is filtered by a simple heuristic and reranked with an off-the-shelf pre-trained language model. We evaluate our approach on two major data-to-text datasets (WebNLG, Cleaned E2E) and analyze its caveats and benefits. Furthermore, we show that our formulation of data-to-text generation opens up the possibility for zero-shot domain adaptation using a general-domain dataset for sentence fusion.- Anthology ID:
- 2020.inlg-1.9
- Volume:
- Proceedings of the 13th International Conference on Natural Language Generation
- Month:
- December
- Year:
- 2020
- Address:
- Dublin, Ireland
- Editors:
- Brian Davis, Yvette Graham, John Kelleher, Yaji Sripada
- Venue:
- INLG
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 60–67
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2020.inlg-1.9/
- DOI:
- 10.18653/v1/2020.inlg-1.9
- Cite (ACL):
- Zdeněk Kasner and Ondřej Dušek. 2020. Data-to-Text Generation with Iterative Text Editing. In Proceedings of the 13th International Conference on Natural Language Generation, pages 60–67, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Data-to-Text Generation with Iterative Text Editing (Kasner & Dušek, INLG 2020)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2020.inlg-1.9.pdf
- Code
- kasnerz/d2t_iterative_editing