<?xml version="1.0" standalone="yes"?>
<Paper uid="H05-1004">
  <Title>Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP), pages 25-32, Vancouver, October 2005. c(c)2005 Association for Computational Linguistics On Coreference Resolution Performance Metrics</Title>
  <Section position="6" start_page="30" end_page="30" type="concl">
    <SectionTitle>
4 Conclusions
</SectionTitle>
    <Paragraph position="0"> A coreference performance metric - CEAF - is proposed in this paper. The CEAF metric is computed based on the best one-to-one map between reference entities and system entities. Finding the best one-to-one map is a maximum bipartite matching problem and can be solved by the Kuhn-Munkres algorithm. Two example entity-pair similarity measures (i.e., a107a16a201 a13 a34a58a29a35a34a41a15 and a107a167a203 a13 a34a49a29a27a34a88a15 ) are proposed, resulting one mention-based CEAF and one entity-based CEAF, respectively. It has been shown that the proposed CEAF metric has fixed problems associated with the MUC link-based F-measure and B-cube F-measure.</Paragraph>
    <Paragraph position="1"> 1This was pointed out by Nanda Kambhatla.</Paragraph>
    <Paragraph position="2"> The proposed metric also has better interpretability than ACE-value.</Paragraph>
  </Section>
class="xml-element"></Paper>