<?xml version="1.0" standalone="yes"?>
<Paper uid="H05-1013">
  <Title>Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP), pages 97-104, Vancouver, October 2005. c(c)2005 Association for Computational Linguistics A Large-Scale Exploration of Effective Global Features for a Joint Entity Detection and Tracking Model</Title>
  <Section position="7" start_page="103" end_page="103" type="concl">
    <SectionTitle>
6 Discussion
</SectionTitle>
    <Paragraph position="0"> In this paper, we have applied the Learning as Search Optimization (LaSO) framework to the entity detection and tracking task. The framework is an excellent choice for this problem, due to the fact that many relevant features for the coreference task (and even for the mention detection task) are highly nonlocal. This non-locality makes models like Markov networks intractable, and LaSO provides an excellent framework for tackling this problem. We have introduced a large set of new, useful features for this task, most speci cally the use of knowledge-based features for helping with the name-to-nominal problem, which has led to a substantial improvement in performance. We have shown that performing joint learning for mention detection and coreference results in a better performing model that pipelined learning. We have also provided a comparison of the contributions of our various feature classes and compared different linkage types for coreference chains.</Paragraph>
    <Paragraph position="1"> In the process, we have developed an ef cient model that is competitive with the best ACE systems.</Paragraph>
    <Paragraph position="2"> Despite these successes, our model is not perfect: the largest source of error is with pronouns. This is masked by the fact that the ACE metric weights pronouns low, but a solution to the EDT problem should handle pronouns well. We intend to explore more complex features for resolving pronouns, and to incorporate these features into our current model.</Paragraph>
    <Paragraph position="3"> We also intend to explore more complex models for automatically extracting knowledge from data that can help with this task and applying this technique to a real application, such as summarization.</Paragraph>
    <Paragraph position="4"> Acknowledgments: We thank three anonymous reviewers for helpful comments. This work was supported by DARPA-ITO grant NN66001-00-1-9814 and NSF grant IIS-0326276.</Paragraph>
  </Section>
class="xml-element"></Paper>