Large pretrained models enable transfer learning to low-resource domains for language generation tasks. However, previous end-to-end approaches do not account for the fact that some generation sub-tasks, specifically aggregation and lexicalisation, can benefit from transfer learning to different extents. To exploit these varying potentials for transfer learning, we propose a new hierarchical approach for few-shot and zero-shot generation. Our approach consists of a three-moduled jointly trained architecture: the first module independently lexicalises the distinct units of information in the input as sentence sub-units (e.g. phrases), the second module recurrently aggregates these sub-units to generate a unified intermediate output, while the third module subsequently post-edits it to generate a coherent and fluent final text. We perform extensive empirical analysis and ablation studies on few-shot and zero-shot settings across 4 datasets. Automatic and human evaluation shows that the proposed hierarchical approach is consistently capable of achieving state-of-the-art results when compared to previous work.
CITATION STYLE
Zhou, G., Lampouras, G., & Iacobacci, I. (2022). Hierarchical Recurrent Aggregative Generation for Few-Shot NLG. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (pp. 2167–2181). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.findings-acl.170
Mendeley helps you to discover research relevant for your work.