Junyun Cui

Legal judgment prediction (LJP) applies Natural Language Processing (NLP) techniques to predict judgment results based on fact descriptions automatically. The present work addresses the growing interest in the application of NLP techniques to the task of LJP. Despite the current performance gap between machines and humans, promising results have been achieved in a variety of benchmark datasets, owing to recent advances in NLP research and the availability of large-scale public datasets. To provide a comprehensive survey of existing LJP tasks, datasets, models, and evaluations, this study presents the following contributions: (1) an analysis of 43 LJP datasets constructed in 9 different languages, together with a classification method of LJP based on three different attributes; (2) a summary of 16 evaluation metrics categorized into 4 different types to evaluate the performance of LJP models for different outputs; (3) a review of 8 legal-domain pretrained models in 4 languages, highlighting four major research directions for LJP; (4) state-of-the-art results for 11 representative datasets from different court cases and an in-depth discussion of the open challenges in this area. This study aims to provide a comprehensive review for NLP researchers and legal professionals to understand the advances in LJP over the past years, and to facilitate further joint efforts towards improving the performance of LJP models.

Legal judgment prediction (LJP) applies Natural Language Processing (NLP) techniques to predict judgment results based on fact descriptions automatically. Recently, large-scale public datasets and advances in NLP research have led to increasing interest in LJP. Despite a clear gap between machine and human performance, impressive results have been achieved in various benchmark datasets. In this paper, to address the current lack of comprehensive survey of existing LJP tasks, datasets, models and evaluations, (1) we analyze 31 LJP datasets in 6 languages, present their construction process and define a classification method of LJP with 3 different attributes; (2) we summarize 14 evaluation metrics under four categories for different outputs of LJP tasks; (3) we review 12 legal-domain pretrained models in 3 languages and highlight 3 major research directions for LJP; (4) we show the state-of-art results for 8 representative datasets from different court cases and discuss the open challenges. This paper can provide up-to-date and comprehensive reviews to help readers understand the status of LJP. We hope to facilitate both NLP researchers and legal professionals for further joint efforts in this problem.

Video prediction has developed rapidly after the booming of deep learning. As an important part of unsupervised representation learning, it plays an important role in anomalous behavior detection, autonomous driving, video games, and other fields. However, the prediction method based on optical flow estimation is susceptible to brightness change and camera shake, and it is difficult to predict occluded objects. While the prediction method based on pixel generation is difficult to fit ambiguous and complex scenes, which leads to a blurry prediction. In this work, we proposed an end-to-end video prediction framework that combines the optical flow estimation module with the pixel generation module by a learnable mask weight to predict high-fidelity videos. To further improve the prediction effect, we introduce adversarial training to the framework. We introduced a frame discriminator and a sequence discriminator to ensure the consistency of the spatio-temporal distribution of predicted video frames and real video frames. The results of experiments on challenging datasets demonstrate the practicability and effectiveness of our proposed video prediction framework. On the one hand, our proposed framework has achieved an equal quality compared with the current latest model, which requires fewer parameters and has a faster prediction speed. On the other hand, the results of ablation experiments demonstrate the effect of fusing different modules and the effectiveness of adversarial training.