We propose a new formulation of the PP attachment problem as a 4-way classification which takes into account the argument or adjunct status of the PP. Based on linguistic diagnostics, we train a 4-way classifier that reaches an average accuracy of (baseline ). Compared to a sequence of binary classifiers, the 4-way classifier reaches better performance and individuates a verb's arguments more accurately, thus improving the acquisition of a crucial piece of information for many NLP applications. .
