Conference paper Open Access

MUSST: A Multilingual Syntactic Simplification Tool

Carolina Scarton; Lucia Specia; Alessio Palmero Aprosio; Sara Tonelli; Tamara Martín Wanton


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>
  <controlfield tag="005">20200120133908.0</controlfield>
  <controlfield tag="001">1042492</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Sheffield</subfield>
    <subfield code="a">Lucia Specia</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">FBK</subfield>
    <subfield code="a">Alessio Palmero Aprosio</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">FBK</subfield>
    <subfield code="a">Sara Tonelli</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">H.I. IBERIA</subfield>
    <subfield code="a">Tamara Martín Wanton</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">158187</subfield>
    <subfield code="z">md5:e65add523e966697650a22582feb5c03</subfield>
    <subfield code="u">https://zenodo.org/record/1042492/files/ijcnlp-demo-3.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2017-11-27</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-h2020-simpatico-692819</subfield>
    <subfield code="o">oai:zenodo.org:1042492</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of Sheffield</subfield>
    <subfield code="a">Carolina Scarton</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">MUSST: A Multilingual Syntactic Simplification Tool</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-h2020-simpatico-692819</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">692819</subfield>
    <subfield code="a">SIMplifying the interaction with Public Administration Through Information technology for Citizens and cOmpanies</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://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;We describe MUSST, a multilingual syntactic simplification tool. The tool supports sentence simplifications for English, Italian and Spanish, and can be easily extended to other languages. Our implementation includes a set of general-purpose simplification rules, as well as a sentence selection module (to select sentences to be simplified) and a confidence model (to select only promising simplifications). The tool was implemented in the context of the European project SIMPATICO on text simplification for Public Administration (PA) texts.&amp;nbsp;Our evaluation on sentences in the PA domain shows that we obtain correct simplifications for &amp;nbsp;76% of the simplified cases in English, 71% of the cases in Spanish. For Italian, the results are lower (38%) but the tool is still under development.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.1042480</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.1042492</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
122
82
views
downloads
All versions This version
Views 12290
Downloads 8260
Data volume 13.4 MB9.5 MB
Unique views 9370
Unique downloads 7757

Share

Cite as