Conference paper Open Access

Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs

Fernando Alva-Manchego; Joachim Bingel; Gustavo Henrique Paetzold; Carolina Scarton; Lucia Specia


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">20200120142556.0</controlfield>
  <controlfield tag="001">1042505</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Copenhagen</subfield>
    <subfield code="a">Joachim Bingel</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Sheffield</subfield>
    <subfield code="a">Gustavo Henrique Paetzold</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University</subfield>
    <subfield code="a">Carolina Scarton</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Univer</subfield>
    <subfield code="a">Lucia Specia</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">179304</subfield>
    <subfield code="z">md5:0ac00bf3c96b14162ecaf1c858441237</subfield>
    <subfield code="u">https://zenodo.org/record/1042505/files/ijcnlp-2017-learning-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:1042505</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of Sheffield</subfield>
    <subfield code="a">Fernando Alva-Manchego</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs</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;Current research in text simplification has been hampered by two central problems: (i) the small amount of high-quality parallel simplification data available, and (ii) the lack of explicit annotations of simplification operations, such as deletions or substitutions, on existing data. While the recently introduced Newsela corpus&amp;nbsp;has alleviated the first problem, simplifications still need to be learned directly from parallel text using black-box, end-to-end approaches rather than from explicit annotations. These complex-simple parallel sentence pairs often differ to such a high degree that generalization becomes difficult. &amp;nbsp;End-to-end models also make it hard to interpret what is actually learned from data. &amp;nbsp;We propose a method that decomposes the task of TS into its sub-problems. We devise a way to automatically identify operations in a parallel corpus and introduce a sequence-labeling approach based on these annotations. Finally, we provide insights on the types of transformations that different approaches can model.&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.1042504</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.1042505</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
36
28
views
downloads
All versions This version
Views 3636
Downloads 2828
Data volume 5.0 MB5.0 MB
Unique views 3030
Unique downloads 2828

Share

Cite as