Pilot Task (LJPJT25)

Legal Judgment Prediction for Japanese Tort cases

In this task, we deal with judgment on civil cases about torts (Civil Code, Art. 709) (opens in a new tab). Japanese law affirms a tort as a negligent or intentional infringement of rights or legal interests that cause a plaintiff to suffer loss or harm. In modern society, torts play an important role in disputes on the internet, for example, cases of defamation and privacy infringement on social media. This new task provides a sandbox for researchers to develop methods using real court case data from Japanese courts.

There are two tasks: Tort Prediction (TP) and Rationale Extraction (RE). A tort case involves two parties: plaintiffs and defendants. Plaintiffs are claimants of the case, arguing that a defendant’s action is a tort, while defendants contest plaintiffs’ arguments.

TP predicts whether a tort is affirmed ($T$, a Boolean value), given undisputed facts ($U$) and arguments from both parties ($P$ from plaintiffs and $D$ from defendants). Undisputed facts are not disputed by any parties or agreed upon by both parties. The final decision on a tort ($T$) should be based on the arguments that are accepted by the judge. Thus the accepted arguments can be considered rationales for the final decision ($T$).

RE identifies the accepted arguments ($R^{P}$ for plaintiffs and $R^{D}$ for defendants, both are sequences of Boolean values, denoting accepted arguments as True) in the parties’ arguments ($P$ and $D$).

To summarise, our tasks take ($U$, $P$, $D$) as input and output ($T$, $R^{P}$, $R^{D}$).

Notice

• This task is a pilot task to see the feasibility and all the training data and test data are provided in Japanese language.
• As we cannot share the dataset with commercial companies, we do not accept participation from commercial companies.
• This task will use the automated evaluation system and leaderboard, which is a prototype of the future COLIEE submission system.
• Participants in this pilot task are invited to join community DISCORD (opens in a new tab), where we will provide technical support for submission.

Acknowledgement

This task is supported by JST JPMJPR236B and Support Centre for Advanced Telecommunication Technology Research.

The dataset used in this task is based on the JTD project (Yamada et al., 2024) supported by JST RISTEX JPMJRX19H3, JST ACT-X JPMJAX20AM and LIC Co., Ltd. We also appreciate Prof. Mihoko Sumida from Hitotsubashi University for her support.

Reference

Hiroaki Yamada, Takenobu Tokunaga, Ryutaro Ohara, Akira Tokutsu, Keisuke Takeshita, and Mihoko Sumida (2024). Japanese tort-case dataset for rationale-supported legal judgment prediction. Artificial Intelligence and Law. https://doi.org/10.1007/s10506-024-09402-0 (opens in a new tab)

Useful resources

• Japanese Law Translation (opens in a new tab) (in English)
• E-gov law search (in Japanese)
  • Search portal (opens in a new tab)
  • Download all Japanese laws as XML (opens in a new tab) (XML schema (opens in a new tab))
  • E-gov law API (opens in a new tab)
• Japanese Court
  • Search Judgments published by the Japanese court (opens in a new tab) (in Japanese)
  • Recently published important judgments (opens in a new tab) (in English, the number of available judgments is very limited)
• [Book] Basic Features of Japanese Tort Law (opens in a new tab) (in English), Keizo Yamamoto, Jan Sramek Verlag, Vienna. ISBN 978-3-7097-0188-1. 2019.