The charge prediction task is to determine appropriate charges for a givencase, which is helpful for legal assistant systems where the user input is factdescription. We argue that relevant law articles play an important role in thistask, and therefore propose an attention-based neural network method to jointlymodel the charge prediction task and the relevant article extraction task in aunified framework. The experimental results show that, besides providing legalbasis, the relevant articles can also clearly improve the charge predictionresults, and our full model can effectively predict appropriate charges forcases with different expression styles.
展开▼
