Control, Generate, Augment: A Scalable Framework for Multi-Attribute Text Generation
Giuseppe Russo, Nora Hollenstein, Claudiu Cristian Musat, Ce Zhang
Abstract
We introduce CGA, a conditional VAE architecture, to control, generate, and augment text. CGA is able to generate natural English sentences controlling multiple semantic and syntactic attributes by combining adversarial learning with a context-aware loss and a cyclical word dropout routine. We demonstrate the value of the individual model components in an ablation study. The scalability of our approach is ensured through a single discriminator, independently of the number of attributes. We show high quality, diversity and attribute control in the generated sentences through a series of automatic and human assessments. As the main application of our work, we test the potential of this new NLG model in a data augmentation scenario. In a downstream NLP task, the sentences generated by our CGA model show significant improvements over a strong baseline, and a classification performance often comparable to adding same amount of additional real data.- Anthology ID:
- 2020.findings-emnlp.33
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 351–366
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.33
- DOI:
- 10.18653/v1/2020.findings-emnlp.33
- Cite (ACL):
- Giuseppe Russo, Nora Hollenstein, Claudiu Cristian Musat, and Ce Zhang. 2020. Control, Generate, Augment: A Scalable Framework for Multi-Attribute Text Generation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 351–366, Online. Association for Computational Linguistics.
- Cite (Informal):
- Control, Generate, Augment: A Scalable Framework for Multi-Attribute Text Generation (Russo et al., Findings 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.findings-emnlp.33.pdf
- Data
- IMDb Movie Reviews