TüReuth Legal at SemEval-2023 Task 6: Modelling Local and Global Structure of Judgements for Rhetorical Role Prediction
Henrik Manegold, Leander Girrbach
The 17th International Workshop on Semantic Evaluation (SemEval-2023) Task 6: legaleval: understanding legal texts Paper
TLDR:
This paper describes our system for SemEval-2023 Task 6: LegalEval: Understanding Legal Texts. We only participate in Sub-Task (A), Predicting Rhetorical Roles. Our final submission achieves 73.35 test set F1 score, ranking 17th of 27 participants. The proposed method combines global and local model
You can open the
#paper-SemEval_38
channel in a separate window.
Abstract:
This paper describes our system for SemEval-2023 Task 6: LegalEval: Understanding Legal Texts. We only participate in Sub-Task (A), Predicting Rhetorical Roles. Our final submission achieves 73.35 test set F1 score, ranking 17th of 27 participants. The proposed method combines global and local models of label distributions and transitions between labels. Through our analyses, we show that especially modelling the temporal distribution of labels contributes positively to performance.