Recent years have witnessed an opportunity to improve trial efficiency and quality by predictive analysis of massive judgment documents. A practical legal judgment prediction (LJP) system should provide a judge with feasible judgment suggestions, including the charges, applicable law articles, and prison term, whereas most existing works focus on only part of the LJP task. Inspired by the impressive success of deep neural networks in a wide range of application scenarios, we propose a multichannel attentive neural network model, MANN, which learns from previous judgment documents and performs the integrated LJP task in a unified framework. In general, MANN takes the textual description of a criminal case as the input for attention-based neural networks to learn its latent feature representations oriented to the case fact, the defendant persona, and relevant law articles. Moreover, we adopt a two-tier structure to empower attentive sequence encoders to hierarchically model the semantic interactions from different parts of case description at both the word and sentence levels. The experiments are conducted on four real-world datasets of criminal cases in mainland China. The experimental results demonstrate that MANN achieves state-of-the-art LJP performance on all evaluation metrics.
16 February 2018 in IEEE Transactions on Information Theory
This paper analyzes the asymptotic performances of fully distributed sequential hypothesis testing procedures as the type-I and type-II error rates approach zero, in the context of a sensor network without a fusion center. In particular, the sensor network is defined by an undirected graph, where each sensor can observe samples over time, access the information from the adjacent sensors, and perform the sequential test based on its own decision statistic. Different from most literature, the sampling process and the information exchange process in our framework take place simultaneously (or, at least in comparable time-scales), thus cannot be decoupled from one another. Our goal is to achieve second-order asymptotically optimal performance at every sensor, i.e., the average detection delay is within a constant gap from the centralized optimal sequential test as the error rates approach zero for the fixed number of sensors. To that end, a type of test procedure that resembles the well-known sequential probability ratio test (SPRT), termed as distributed SPRT (DSPRT) in this paper, is studied based on two message-passing schemes, respectively. The first scheme features the dissemination of the raw samples. In specific, every sample propagates over the network by being relayed from one sensor to another until it reaches all the sensors in the network. Although the sample propagation-based DSPRT is shown to yield the asymptotically optimal performance at each sensor, it incurs excessive intersensor communication overhead due to the exchange of raw samples with index information. The second scheme adopts the consensus algorithm, where the local decision statistic is exchanged between sensors instead of the raw samples, thus significantly lowering the communication requirement compared with the first scheme. In particular, the decision statistic for DSPRT at each sensor is updated by the weighted average of the decision statistics in the neighborhood at every message-passing step. We show that, under certain regularity conditions, the consensus algorithm-based DSPRT also yields the secondorder asymptotically optimal performance at all sensors given a fixed number of sensors. Our asymptotic analyses of the two message-passing-based DSPRTs are then corroborated by simulations using the Gaussian and Laplacian samples.
5 March 2014 in IEEE Journal of Selected Topics in Signal Processing
This paper considers the security issue of the reputation systems, which make great use of social networks, to form the reputation scores of a certain participant in the network by collecting ratings from others. To prevent the damage caused by the intentional injection of dishonest ratings, termed as reputation attack, we aim to detect such attack as soon as possible after its occurrence by sequentially observing the rating samples at a single or multiple agents. We propose a discrete probability model to characterize the rating samples based on which the sequential change detection framework can be applied. First for the single-agent case, we develop a sequential attack detector based on the generalized likelihood ratio (GLR) that is robust to a wide range of attacking strategies. Then, for the multi-agent case, where the distributed agents collect ratings and communicate with a central manager to make the decision, we propose a novel multi-agent sequential attack detector that can effectively exploit the different number of attacked agents to increase the detection speed, and exhibits a second-order asymptotic optimality for any given number of attacked agents if the rating distribution under attack can be specified. Finally, we propose a decentralized version of the multi-agent attack detector based on the level-triggered sampling of the local statistic at each agent, which essentially constitutes an adaptive transmission scheme between the distributed agents and the central manager. The decentralized detector incurs only a minor increase in detection delay compared with the centralized counterpart while substantially reduces the communication overhead for attack detection in the multi-agent reputation systems.
The task of prison term prediction is to predict the term of penalty based on textual fact description for a certain type of criminal case. Recent advances in deep learning frameworks inspire us to propose a two-step method to address this problem. To obtain a better understanding and more specific representation of the legal texts, we summarize a judgment model according to relevant law articles and then apply it in the extraction of case feature from judgment documents. By formalizing prison term prediction as a regression problem, we adopt the linear regression model and the neural network model to train the prison term predictor. In experiments, we construct a realworld dataset of theft case judgment documents. Experimental results demonstrate that our method can effectively extract judgment-specific case features from textual fact descriptions. The best performance of the proposed predictor is obtained with a mean absolute error of 3.2087 months, and the accuracy of 72.54% and 90.01% at the error upper bounds of three and six months, respectively.