Transformers for Multi-Intent Classification and Slot Filling of Supreme Court Decisions Related to Sexual Violence Law

Abstract

Sexual violence is a pervasive and complex issue that demands an immediate and comprehensive solution. The previous study titled 'LAW-U: Legal Guidance Through Artificial Intelligence Chatbot for Sexual Violence Victims and Survivors' highlighted the crucial role of technology in addressing this problem. The current study aims to overcome limitations in the previous study by investigating the use of transformer-based models for multi-intent classification of Thai Supreme Court decision fragments related to Section 276 of the Thai Criminal Code. Utilizing various evaluation matrices, the study evaluates the effectiveness of transfer learning through transformer-based pre-trained language models against a Word2Vec-based support vector machine to detect criminal intents from decision fragments. The results demonstrate that transformer-based models, particularly XLM-RoBERTaBASE, outperform the Word2Vec-based support vector machine in multi-intent classification. The macro average F1-score of 0.77 and micro average F1-score of 0.78 achieved by the best-performing model indicates the effectiveness of pre-trained transformers with fine-tuning. The study also employs a t-SNE visualization to gain insights into the overlapping between criminal intents and the areas where misclassifications occur. The visualization reveals that misclassification occur between closely related or overlapping intents, especially when decision fragments have multiple intents. Overall, the study contributes to the field of legal technology by creating a model that can accurately classify criminal intents related to Section 276, which can be extrapolated to other sexual violence laws. The model will be used to train the updated version of LAW-U, specifically called LAW-U-RoBERTa, which will provide legal recommendations to sexual violence survivors and empower them to reaffirm their inherent rights through seeking justice. The study demonstrates the potential of artificial intelligence chatbots to support survivors of sexual violence and contribute to the fight against the pervasive problem of sexual violence.