Conference paper Open Access

On the Importance of Drill-Down Analysis for Assessing Gold Standards and Named Entity Linking Performance

Odoni, Fabian; Kuntschik, Philipp; Brasoveanu, Adrian M.P.; Weichselbraun, Albert


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Named Entity Linking</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Evaluation</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Drill-Down Analysis</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Resource Versioning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Linked Data Quality</subfield>
  </datafield>
  <controlfield tag="005">20190410032322.0</controlfield>
  <controlfield tag="001">2543341</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">10-13 September 2018</subfield>
    <subfield code="g">SEMANTiCS 2018</subfield>
    <subfield code="a">14th International Conference on Semantic Systems</subfield>
    <subfield code="c">Vienna, Austria</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Swiss Institute for Information Science, University of Applied Sciences Chur</subfield>
    <subfield code="a">Kuntschik, Philipp</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">MODUL Technology GmbH, Vienna, Austria</subfield>
    <subfield code="a">Brasoveanu,  Adrian M.P.</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Swiss Institute for Information Science, University of Applied Sciences Chur</subfield>
    <subfield code="a">Weichselbraun, Albert</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">345679</subfield>
    <subfield code="z">md5:17fd0e44e7800a45e66aba52040dd762</subfield>
    <subfield code="u">https://zenodo.org/record/2543341/files/Odoni_Semantics2018.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="y">Conference website</subfield>
    <subfield code="u">https://2018.semantics.cc/</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2018-09-12</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-invid-h2020</subfield>
    <subfield code="o">oai:zenodo.org:2543341</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Swiss Institute for Information Science, University of Applied Sciences Chur</subfield>
    <subfield code="a">Odoni, Fabian</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">On the Importance of Drill-Down Analysis for Assessing Gold Standards and Named Entity Linking Performance</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-invid-h2020</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">687786</subfield>
    <subfield code="a">In Video Veritas – Verification of Social Media Video Content for the News Industry</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">http://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;Rigorous evaluations and analyses of evaluation results are key towards improving Named Entity Linking systems. Nevertheless, most current evaluation tools are focused on benchmarking and comparative evaluations. Therefore, they only provide aggregated statistics such as precision, recall and F1-measure to assess system performance and no means for conducting detailed analyses up to the level of individual annotations. This paper addresses the need for transparent benchmarking and fine-grained error analysis by introducing Orbis, an extensible framework that supports drill-down analysis, multiple annotation tasks and resource versioning. Orbis complements approaches like those deployed through the GERBIL and TAC KBP tools and helps developers to better understand and address shortcomings in their Named Entity Linking tools. We present three uses cases in order to demonstrate the usefulness of Orbis for both research and production systems: (i) improving Named Entity Linking tools; (ii) detecting gold standard errors; and (iii) performing Named Entity Linking evaluations with multiple versions of the included resources.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1016/j.procs.2018.09.004</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
37
29
views
downloads
Views 37
Downloads 29
Data volume 10.0 MB
Unique views 32
Unique downloads 25

Share

Cite as