Abstract
Recent neural models for data-to-text generation are mostly based on data-driven end-to-end training over encoder-decoder networks. Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data. This is a critical issue especially in domains that require inference or calculations over raw data. In this paper, we attempt to improve the fidelity of neural data-to-text generation by utilizing pre-executed symbolic operations. We propose a framework called Operation-guided Attention-based sequence-to-sequence network (OpAtt), with a specifically designed gating mechanism as well as a quantization module for operation results to utilize information from pre-executed operations. Experiments on two sports datasets show our proposed method clearly improves the fidelity of the generated texts to the input structured data.- Anthology ID:
- D18-1422
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3879–3889
- Language:
- URL:
- https://aclanthology.org/D18-1422
- DOI:
- 10.18653/v1/D18-1422
- Cite (ACL):
- Feng Nie, Jinpeng Wang, Jin-Ge Yao, Rong Pan, and Chin-Yew Lin. 2018. Operation-guided Neural Networks for High Fidelity Data-To-Text Generation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3879–3889, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Operation-guided Neural Networks for High Fidelity Data-To-Text Generation (Nie et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/naacl24-info/D18-1422.pdf
- Data
- RotoWire, WikiBio