Previous systems that automatically tag text with FrameNet labels have been trained from the FrameNet example data, as there is no FrameNet annotated corpus. The FrameNet data is systematically biased by the criteria for the examples ’ selection, as annotators attempt to select simple sentences that include the target word. Instead of using the FrameNet examples, we train a maximum entropy model classifier to identify verb frames on text from the Penn Treebank. We use examples of verbs with only one entry in FrameNet as training data, and evaluate the system on human annotated text from the Wall Street Journal. We accurately identify the frame used by 76 % of finite verbs. We also investigate how well the system performs on verbs it has not encountered before. This task examines the feasibility of using the system to automatically extend the coverage of FrameNet by classifying verbs with no FrameNet entries. The classifier accurately assigns a frame to 55 % of instances of verbs it has not been trained on. 1