We study the problem of machine comprehension of court judgments and generation of descriptive tags for judgments. Our approach makes use of a legal taxonomy unmapped: inline-formula unmapped: math unmapped: mi D, which serves as a dictionary of canonicalized legal concepts. Given a court judgment J, our method identifies the key contents of J and then applies Word2Vec and BERT-based models to select a short list unmapped: inline-formula unmapped: math unmapped: msub unmapped: mrow unmapped: mi Tunmapped: mrow unmapped: mi J of terms/phrases from the taxonomy unmapped: inline-formula unmapped: math unmapped: mi D as descriptive tags of J. The tag set unmapped: inline-formula unmapped: math unmapped: msub unmapped: mrow unmapped: mi Tunmapped: mrow unmapped: mi J suggests concepts that are relevant to or associative with J and provides a simple mechanism for readers of J to compose associative queries for effective judgment recommendation. Our prototype system implemented on the Hong Kong Legal Information Institute (HKLII) platform shows that our method provides a highly effective tool that assists users in exploring a judgment corpus and in obtaining relevant judgment recommendation.