CCAC 2023 第三届智慧论辩评测（AI-Debater）

针对给定的话题和原始论点，由参赛模型自动生成反驳原始论点的5个句子（称为反论点）。

• 输入：Should the phrase "under God" be retained in the Pledge of Allegiance?<tab>the under God line is actually a relatively new addition and can therefore be easily removed without significant consequences.
• 输出：
  Just because something is new doesn't mean it lacks importance or significance, and removing it can have unforeseen consequences.
  Ignoring the historical and constitutional significance of the "under God" line in the Pledge of Allegiance is a dangerous oversimplification that fails to recognize the phrase's cultural and symbolic importance to American identity.
  ……

ROUGE-L

1. https://eval.ai/challenge/1449/leaderboard/3606
2. Yuan, Jian, Liying Cheng, Ruidan He, Yinzi Li, Lidong Bing, Zhongyu Wei, Qin Liu, Chenhui Shen, Shuonan Zhang, Changlong Sun, Luo Si, Changjian JIang and Xunjing Huang. Overview of Argumentative Text Understanding for AI Debater Challenge. NLPCC 2021.
3. Lu Ji, Zhongyu Wei, Xiangkun Hu, Yang Liu, Qi Zhang and XuanJing Huang. Incorporating argument-level interactions for persuasion comments evaluation using co-attention model. COLING 2018.
4. Lu Ji, Zhongyu Wei, Jing Li, Qi Zhang and Xuanjing Huang. Discrete Argument Representation Learning for Interactive Argument Pair Identification. NAACL 2021.
5. Jian Yuan, Zhongyu Wei, Donghua, Zhao, Qi Zhang and Changjian Jiang. Leveraging Argumentation Knowledge Graph for Interactive Argument Pair Identification. ACL 2021 findings.
6. Xinyu Hua, Zhe Hu, and Lu Wang. 2019. Argument Generation with Retrieval, Planning, and Realization. ACL 2019.
7. Milad Alshomary, Shahbaz Syed, Arkajit Dhar, Martin Potthast, and Henning Wachsmuth. 2021. Counter-Argument Generation by Attacking Weak Premises. ACL 2021 findings.