AEG: Argumentative Essay Generation via A Dual-Decoder Model with Content Planning

Jianzhu Bao, Yasheng Wang, Yitong Li, Fei Mi, Ruifeng Xu


Abstract
Argument generation is an important but challenging task in computational argumentation.Existing studies have mainly focused on generating individual short arguments, while research on generating long and coherent argumentative essays is still under-explored.In this paper, we propose a new task, Argumentative Essay Generation (AEG).Given a writing prompt, the goal of AEG is to automatically generate an argumentative essay with strong persuasiveness.We construct a large-scale dataset, ArgEssay, for this new task and establish a strong model based on a dual-decoder Transformer architecture.Our proposed model contains two decoders, a planning decoder (PD) and a writing decoder (WD), where PD is used to generate a sequence for essay content planning and WD incorporates the planning information to write an essay.Further, we pre-train this model on a large news dataset to enhance the plan-and-write paradigm.Automatic and human evaluation results show that our model can generate more coherent and persuasive essays with higher diversity and less repetition compared to several baselines.
Anthology ID:
2022.emnlp-main.343
Original:
2022.emnlp-main.343v1
Version 2:
2022.emnlp-main.343v2
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5134–5148
Language:
URL:
https://aclanthology.org/2022.emnlp-main.343
DOI:
10.18653/v1/2022.emnlp-main.343
Bibkey:
Cite (ACL):
Jianzhu Bao, Yasheng Wang, Yitong Li, Fei Mi, and Ruifeng Xu. 2022. AEG: Argumentative Essay Generation via A Dual-Decoder Model with Content Planning. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5134–5148, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
AEG: Argumentative Essay Generation via A Dual-Decoder Model with Content Planning (Bao et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.343.pdf