Coreference Clustering Task

(Redirected from Coreference Resolution)
Jump to: navigation, search

A Coreference Clustering Task is a clustering task where all referencers must be grouped into coreference clusters (that share a coreference relation).



  • (Sawhney & Wang, 2015) ⇒ Kartik Sawhney and Rebecca Wang (2015) "Coreference Resolution"
    • Overview - Coreference resolution refers to the task of clustering different mentions referring to the same entity. This is particularly useful in other NLP tasks, including retrieving information about specific named entities, machine translation, among others. In this report, we discuss our approach, implementation and observations for a few baseline systems, a rule-based system, and a classifier-based system. To quantify the effectiveness of our implementation, we use the MUC and B^3 measures (precision, recall and F1) for coreference evaluation. The difference in the two scoring metrics in how they define a coreference set within a text (in terms of links or in terms of classes or clusters) results in interesting observations as we discuss in the report.