Building a High-quality and Data-driven Legal Intelligent System

In the last decades, traditional information sources have largely been replaced by their digital counterparts, legal information users (ordinary people, legal librarians and researchers, lawyers, or judges) thus rely on digital information sources as assistance to solve legal problems. Making efficient use of these digital resources requires advanced techniques, such as information retrieval (IR), evidence building, and argument generation emerge. Legal IR aims to find proper legal information quickly and accurately, usually acts as the foundation of evidence building and argument generation, legal evidence building is to find a set of facts that can be inference for a claim, argument generation focuses on generating complete arguments out of facts. Legal evidence building and argument generation are two innovative but useful tasks which have been rarely touched by researcher because of the immensity and complexity of legal information. Therefore, this project will explore newly developed techniques in natural language processing and deep learning to build efficient and robust IR, evidence, and argument generation systems in legal domain, which will benefit legal information users for better decision making.

Related papers

Chen, H., Wu, L., Chen, J., Lu, W., & Ding, J. (2022). A comparative study of automated legal text classification using random forests and deep learning. Information Processing & Management, 59(2), 102798.

Chen, H., Pieptea, L. F., & Ding, J. (2022). Construction and evaluation of a high-quality corpus for legal intelligence using semiautomated approaches. IEEE Transactions on Reliability, 71(2), 657-673.

Tang, M., Su, C., Chen, H., Qu, J., & Ding, J. (2020, December). SALKG: a semantic annotation system for building a high-quality legal knowledge graph. In 2020 IEEE International Conference on Big Data (Big Data) (pp. 2153-2159). IEEE.