Second language (L2) grammar learning is difficult. Two frameworks--the psycholinguistic lexical bottleneck hypothesis and the neurocognitive declarative/procedural model--predict that faster L2 lexical processing should facilitate L2 incidental grammar learning. We tested these predictions in a pretest-posttest syntactic adaptation study of English relative-clause attachment preferences. First-language German speakers listened to relative clauses disambiguated to the English low-attachment preference ("secretaries of the professor who is/naps at home")--via either a copula (e.g., "is"), which should be processed rapidly (copula group; n = 48), or a lexical verb (e.g., "naps"), which should be processed more slowly (lexical group; n = 48). Only the copula group showed significant pretest-to-posttest learning. Moreover, the amount of learning was predicted by procedural learning abilities in the copula group, but by vocabulary size in the lexical group. The results, which are consistent with both frameworks, show that the L2 lexicon impacts L2 grammar learning, and reveal moderating psycholinguistic and neurocognitive variables.