PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation

Zhe Hu, Hou Pong Chan, Jiachen Liu, Xinyan Xiao, Hua Wu, Lifu Huang


Abstract
Despite recent progress of pre-trained language models on generating fluent text, existing methods still suffer from incoherence problems in long-form text generation tasks that require proper content control and planning to form a coherent high-level logical flow. In this work, we propose PLANET, a novel generation framework leveraging autoregressive self-attention mechanism to conduct content planning and surface realization dynamically. To guide the generation of output sentences, our framework enriches the Transformer decoder with latent representations to maintain sentence-level semantic plans grounded by bag-of-words. Moreover, we introduce a new coherence-based contrastive learning objective to further improve the coherence of output. Extensive experiments are conducted on two challenging long-form text generation tasks including counterargument generation and opinion article generation. Both automatic and human evaluations show that our method significantly outperforms strong baselines and generates more coherent texts with richer contents.
Anthology ID:
2022.acl-long.163
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2288–2305
Language:
URL:
https://aclanthology.org/2022.acl-long.163
DOI:
10.18653/v1/2022.acl-long.163
Bibkey:
Cite (ACL):
Zhe Hu, Hou Pong Chan, Jiachen Liu, Xinyan Xiao, Hua Wu, and Lifu Huang. 2022. PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2288–2305, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation (Hu et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.163.pdf