Knowledge Augmented Entity and Relation Extraction for Legal Documents with Hypergraph Neural Network

With the continuous progress of digitization in Chinese judicial institutions, a substantial amount of electronic legal document information has been accumulated. To unlock its potential value, entity and relation extraction for legal documents has emerged as a crucial task. However, existing methods often lack domain-specific knowledge and fail to account for the unique characteristics of the judicial domain. In this paper, we propose an entity and relation extraction algorithm based on hypergraph neural network (Legal-KAHRE) for drug-related judgment documents. Firstly, we design a candidate span generator based on neighbor-oriented packing strategy and biaffine mechanism, which identifies spans likely to contain entities. Secondly, we construct a legal dictionary with judicial domain knowledge and integrate it into text encoding representation using multi-head attention. Additionally, we incorporate domain-specific cases like joint crimes and combined punishment for multiple crimes into the hypergraph structure design. Finally, we employ a hypergraph neural network for higher-order inference via message passing. Experimental results on the CAIL2022 information extraction dataset demonstrate that our method significantly outperforms existing baseline models.

💡 Research Summary

The paper addresses the problem of extracting entities and relations from Chinese criminal judgment documents, focusing on drug‑related cases. Existing approaches either rely on pipeline architectures that treat named entity recognition (NER) and relation extraction (RE) as separate steps, or on joint models that still lack domain‑specific knowledge and fail to capture the complex legal constructs such as “joint crimes” and “combined punishment for multiple crimes.” To overcome these shortcomings, the authors propose Legal‑KAHRE (Knowledge‑Augmented Hypergraph‑based Entity and Relation Extraction), a four‑component system that integrates a domain dictionary, a novel span generator, and a custom hypergraph neural network (HGNN).

1. Candidate Span Generator – The generator adopts the neighbor‑oriented packing strategy from recent work, inserting special markers