“…The mere task of producing the same results as those produced by humans is difficult and largely unsolved. There is nonetheless a strong interest in automatically identifying coreference links as they are needed by information extraction to merge different pieces of information referring to the same entity (McCarthy and Lehnert, 1995), by text summarization to produce a coherent and fluent summary (Azzam et al, 1999;Steinberger et al, 2007), by question answering to disambiguate references along a document (Morton, 1999;Vicedo and Ferrández, 2006), and by machine translation to translate pronouns correctly. Recently, state-of-the-art coreference resolution systems have been helpful for sentiment analysis (Nicolov et al, 2008), textual entailment Abad et al, 2010), citation matching and databases (Wick et al, 2009), machine reading (Poon et al, 2010), for learning narrative schemas (Chambers and Jurafsky, 2008), and for recovering implicit arguments (Gerber and Chai, 2010;Ruppenhofer et al, 2010).…”