TY - GEN
T1 - AEG
T2 - 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
AU - Bao, Jianzhu
AU - Wang, Yasheng
AU - Li, Yitong
AU - Mi, Fei
AU - Xu, Ruifeng
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85149438618
U2 - 10.18653/v1/2022.emnlp-main.343
DO - 10.18653/v1/2022.emnlp-main.343
M3 - 会议稿件
AN - SCOPUS:85149438618
T3 - Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
SP - 5134
EP - 5148
BT - Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
A2 - Goldberg, Yoav
A2 - Kozareva, Zornitsa
A2 - Zhang, Yue
PB - Association for Computational Linguistics (ACL)
Y2 - 7 December 2022 through 11 December 2022
ER -