Global joint models for coreference resolution and named entity classification

95 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Learning Structured Perceptrons for Coreference Resolution with Latent Antecedents and Non-local Features (2014, background): “We also report the CoNLL average (also known as MELA ; Denis and Baldridge (2009)), i.e., the arithmetic mean of MUC, B 3 , and CEAF e .”
Inference Protocols for Coreference Resolution (2011, background): “Similar to Pascal and Baldridge (2009), we observe that this improves accuracy — the reader is referred to Pascal and Baldridge (2009) for more details.”
A Constrained Latent Variable Model for Coreference Resolution (2013, methodology): “CL3M is inspired by a few ideas from the literature: (a) the popular BestLeft-Link inference approach to coreference (Ng and Cardie, 2002; Bengtson and Roth, 2008), and (b) the injection of domain knowledge-based constraints for structured prediction (Roth and Yih, 2004; Clarke and Lapata, 2006; Cha”
Which Coreference Evaluation Metric Do You Trust? A Proposal for a Link-based Entity Aware Metric (2016, methodology): “As mentioned by Denis and Baldridge (2009b), CEAF ignores all correct decisions of unaligned response entities that may lead to unreliable results.”
CoNLL-2011 Shared Task: Modeling Unrestricted Coreference in OntoNotes (2011, methodology): “We settled on the MELA metric by Denis and Baldridge (2009), which takes a weighted average of three metrics: MUC, B-CUBED, and CEAF.”