SECaps: A Sequence Enhanced Capsule Model for Charge Prediction
This work addresses a domain-specific problem for legal professionals by improving charge prediction accuracy, particularly for rare charges, but it is incremental as it builds on existing capsule network approaches.
The paper tackles the problem of automatic charge prediction in legal cases, where existing methods struggle with few-shot charges, and proposes the SECaps model, which achieves 4.5% and 6.4% absolute improvements in Macro F1 on two datasets compared to state-of-the-art methods.
Automatic charge prediction aims to predict appropriate final charges according to the fact descriptions for a given criminal case. Automatic charge prediction plays a critical role in assisting judges and lawyers to improve the efficiency of legal decisions, and thus has received much attention. Nevertheless, most existing works on automatic charge prediction perform adequately on high-frequency charges but are not yet capable of predicting few-shot charges with limited cases. In this paper, we propose a Sequence Enhanced Capsule model, dubbed as SECaps model, to relieve this problem. Specifically, following the work of capsule networks, we propose the seq-caps layer, which considers sequence information and spatial information of legal texts simultaneously. Then we design a attention residual unit, which provides auxiliary information for charge prediction. In addition, our SECaps model introduces focal loss, which relieves the problem of imbalanced charges. Comparing the state-of-the-art methods, our SECaps model obtains 4.5% and 6.4% absolutely considerable improvements under Macro F1 in Criminal-S and Criminal-L respectively. The experimental results consistently demonstrate the superiorities and competitiveness of our proposed model.