@inproceedings{zhou-etal-2022-hierarchical,
title = "Hierarchical Recurrent Aggregative Generation for Few-Shot {NLG}",
author = "Zhou, Giulio and
Lampouras, Gerasimos and
Iacobacci, Ignacio",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.findings-acl.170/",
doi = "10.18653/v1/2022.findings-acl.170",
pages = "2167--2181",
abstract = "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 in 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."
}
Markdown (Informal)
[Hierarchical Recurrent Aggregative Generation for Few-Shot NLG](https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.findings-acl.170/) (Zhou et al., Findings 2022)
ACL