The shared task of "Argumentative Text Understanding for AI Debater" is organized by Fudan University and Alibaba Group, it will be held together with the NLPCC 2021 (http://tcci.ccf.org.cn/conference/2021/cfpt.php).
Argument and debate are fundamental capabilities of human intelligence, essential for a wide range of human activities, and common to all human societies. With an aim of developing an autonomous debating system, we make an initial step to understanding the argumentative text of debating in this shared task, including three tracks, namely, supporting material identification (track 1), argument pair identification from online forum (track 2) and argument pair extraction from peer review and rebuttal (track 3).
In track 1, we present the fundamental scenario of supporting material identification for a given debating topic. In tracks 2&3, we focus on the understanding of the dialogical argumentative text in two domains, i.e., online debating forum and scientific paper review process. We provide three datasets in this task, one for each track.
You are welcomed very much to participate in this event.
Let's hope in this fall, the vaccine passport will be issued and accepted for convenient international travel. Thus, we will have a chance to gather together in Qingdao, China!
=== TIMELINE ===
April 10, 2021 Registration starts.
April 25, 2021 Training data release (Phase 1 starts).
May 20, 2021 Registration ends.
May 25, 2021 Testing data release (Phase 1 ends and Phase 2 starts). Participants that outperform the given baseline are permitted to enter this phase.
June 15, 2021 Phase 2 ends.
June 25, 2021 Evaluation results release.
July 15, 2021 Task report submission deadline.
August 14, 2021 Camera-ready paper submission deadline.
October 13-17, 2021 Awards Ceremony and Challenge Workshop (during the 10th CCF International Conference on Natural Language Processing and Chinese Computing) China Computational Linguistics Conference, the winning teams are invited to share the competition experience and models.