We provide a new framework for using text as data in empirical models. The framework identifies salient information in unstructured text that can control for multidimensional heterogeneity among assets. We demonstrate the efficacy of the framework by re-examining principal-agent problems in...

We use real estate firms to examine how asset liquidation values influence a firm's financing choices, since the productivity and quality of each asset is observable and potential measures of an asset's liquidation value are easier to ascertain ex-ante. We show that compared to firms that issue...