Overview of SMP-CAIL2020-Argmine: The Interactive Argument-Pair Extraction in Judgement Document Challenge

In this paper we present the results of the Interactive Argument-Pair Extraction in Judgement DocumentChallenge held by both the Chinese AI and Law Challenge (CAIL) and the Chinese National Social MediaProcessing Conference (SMP), and introduce the related data set – SMP-CAIL2020-Argmine. The taskchallenged participants to choose the correct argument among five candidates proposed by the defense torefute or acknowledge the given argument made by the plaintiff, providing the full context recorded in thejudgement documents of both parties. We received entries from 63 competing teams, 38 of which scoredhigher than the provided baseline model (BERT) in the first phase and entered the second phase. The bestperforming system in the two phases achieved accuracy of 0.856 and 0.905, respectively. In this paper, wewill present the results of the competition and a summary of the systems, highlighting commonalities andinnovations among participating systems. The SMP-CAIL2020-Argmine data set and baseline models? havebeen already released.