Integer Linear Programming for Coreference Resolution

Computational Models of Anaphora

“…Another example is mention detection: Daume & Marcu (2005), for instance, showed that this task, too, is best performed jointly with anaphora resolution-a finding that lies at the core of the "end-to-end" neural model currently dominating anaphora resolution and discussed in Section 6 (Lee et al 2017). The realization that many such tasks are best performed jointly led to numerous models adopting joint inference architectures such as the Integer Linear Programming (ilp) model (Rizzolo & Roth 2016), a form of constraint programming in which constraints can be imposed on variables modeling the outcome of separate classifiers (e.g., for coreference and anaphoricity detection). The use of ilp for coreference was popularized by Denis & Balridge (2007), who applied the framework to joint anaphoricity detection and anaphora resolution, but this approach has been widely applied in anaphora resolution (Iida & Poesio 2011).…”

“…Bergsma (2016) and Versley et al (2016) cover feature extraction from corpora and the use of lexical and commonsense knowledge, respectively. Joint inference is covered by Rizzolo & Roth (2016), and detection of nonanaphoricity and nonreference is discussed in Uryupina et al (2016).…”