Abstract
While neural, encoder-decoder models have had significant empirical success in text generation, there remain several unaddressed problems with this style of generation. Encoder-decoder models are largely (a) uninterpretable, and (b) difficult to control in terms of their phrasing or content. This work proposes a neural generation system using a hidden semi-markov model (HSMM) decoder, which learns latent, discrete templates jointly with learning to generate. We show that this model learns useful templates, and that these templates make generation both more interpretable and controllable. Furthermore, we show that this approach scales to real data sets and achieves strong performance nearing that of encoder-decoder text generation models.- Anthology ID:
- D18-1356
- 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:
- 3174–3187
- Language:
- URL:
- https://aclanthology.org/D18-1356
- DOI:
- 10.18653/v1/D18-1356
- Cite (ACL):
- Sam Wiseman, Stuart Shieber, and Alexander Rush. 2018. Learning Neural Templates for Text Generation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3174–3187, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Learning Neural Templates for Text Generation (Wiseman et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/D18-1356.pdf
- Code
- harvardnlp/neural-template-gen + additional community code
- Data
- WikiBio