The paper presents a novel approach to relation extraction using the shortest path between two entities in the dependency graph. The authors argue that the information required to establish a relationship between two named entities is primarily captured by the shortest path in the dependency graph. Experiments on the ACE corpus show that this new shortest path dependency kernel outperforms a recent approach based on dependency tree kernels. The paper discusses the importance of syntactic information in relation extraction and how the shortest path kernel can leverage this information more effectively. The authors also introduce a kernel function that efficiently computes the similarity between two dependency paths, which is used with Support Vector Machines (SVMs) for training the model. The experimental results demonstrate significant improvements in accuracy compared to previous methods, particularly when using a CFG parser for dependency extraction. The paper concludes by discussing future work, including the integration of entity recognition and the exploration of deep dependencies.The paper presents a novel approach to relation extraction using the shortest path between two entities in the dependency graph. The authors argue that the information required to establish a relationship between two named entities is primarily captured by the shortest path in the dependency graph. Experiments on the ACE corpus show that this new shortest path dependency kernel outperforms a recent approach based on dependency tree kernels. The paper discusses the importance of syntactic information in relation extraction and how the shortest path kernel can leverage this information more effectively. The authors also introduce a kernel function that efficiently computes the similarity between two dependency paths, which is used with Support Vector Machines (SVMs) for training the model. The experimental results demonstrate significant improvements in accuracy compared to previous methods, particularly when using a CFG parser for dependency extraction. The paper concludes by discussing future work, including the integration of entity recognition and the exploration of deep dependencies.