Structured representations for coreference resolution Coreference resolution is the task of determining which mentions in a text are used to refer to the same entity. Inherently, coreference resolution is a structured task, as the output consists of sets of coreferring expressions. This complex structure poses challenges for model development and error analysis. In this talk, we present machine learning and error analysis frameworks for coreference resolution that account for the structure. Our machine learning framework casts coreference resolution as latent structured prediction. It yields a unified representation of approaches, ranging from simple binary classification models to sophisticated entity-centric approaches. We employ the error analysis framework to perform an in-depth analysis and comparison of popular approaches implemented in our machine learning framework on a benchmark data set.