TY - GEN
T1 - Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Control
AU - Li, Yunzhe
AU - Chen, Qian
AU - Yan, Weixiang
AU - Zhang, Qinglin
AU - Wang, Wen
AU - Sundaram, Hari
N1 - Publisher Copyright:
© 2024 Association for Computational Linguistics.
PY - 2024
Y1 - 2024
N2 - Existing works on outline-conditioned text generation typically aim to generate text using provided outlines as rough sketches, such as Keywords and phrases. However, these approaches make it challenging to control the quality of text generation and assess consistency between outlines and generated texts due to lack of clarity and rationality of the rough outlines. In this paper, we introduce a novel text generation task called Precise Outline-conditioned Generation, which requires generating stories based on specific, sentence-level outlines. To facilitate research on this task, we construct two new datasets, WPOG and CDM. We provide strong baselines based on fine-tuning models such as BART and GPT-2, and evaluating zero-shot performance of models such as ChatGPT and Vicuna. Furthermore, we identify an issue of imbalanced utilization of the outline information in the precise outline-conditioned generation, which is ubiquitously observed across fine-tuned models and zero-shot inference models. To address this issue, we propose an explicit outline utilization control approach and a novel framework that leverages the task duality between summarization and generation. Experimental results show that the proposed approaches effectively alleviate the issue of imbalanced outline utilization and enhance the quality of precise outline-conditioned text generation for both fine-tuning and zero-shot settings.
AB - Existing works on outline-conditioned text generation typically aim to generate text using provided outlines as rough sketches, such as Keywords and phrases. However, these approaches make it challenging to control the quality of text generation and assess consistency between outlines and generated texts due to lack of clarity and rationality of the rough outlines. In this paper, we introduce a novel text generation task called Precise Outline-conditioned Generation, which requires generating stories based on specific, sentence-level outlines. To facilitate research on this task, we construct two new datasets, WPOG and CDM. We provide strong baselines based on fine-tuning models such as BART and GPT-2, and evaluating zero-shot performance of models such as ChatGPT and Vicuna. Furthermore, we identify an issue of imbalanced utilization of the outline information in the precise outline-conditioned generation, which is ubiquitously observed across fine-tuned models and zero-shot inference models. To address this issue, we propose an explicit outline utilization control approach and a novel framework that leverages the task duality between summarization and generation. Experimental results show that the proposed approaches effectively alleviate the issue of imbalanced outline utilization and enhance the quality of precise outline-conditioned text generation for both fine-tuning and zero-shot settings.
UR - http://www.scopus.com/inward/record.url?scp=85189943380&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85189943380&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85189943380
T3 - EACL 2024 - 18th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
SP - 2362
EP - 2377
BT - EACL 2024 - 18th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
A2 - Graham, Yvette
A2 - Purver, Matthew
A2 - Purver, Matthew
PB - Association for Computational Linguistics (ACL)
T2 - 18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024
Y2 - 17 March 2024 through 22 March 2024
ER -