This paper examines the use of an unsupervised statistical model for determining the attachment of ambiguous coordinate phrases (CP) of the form n l p n2 cc n3. The model presented here is based on JAR98], an unsupervised model for determining prepositional phrase attachment. After training on unannotated 1988 Wall Street Journal text, the model performs at 72% accuracy on a development set from sections 14 through 19 of the WSJ TreeBank [MSM93]. 1 Introduction [AR98] models.
