Konferans bildirisi Açık Erişim

Waste Not: Meta-Embedding of Word and Context Vectors

Degirmenci, Selin; Gerek, Aydin; Ganiz, Murat Can


MARC21 XML

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Waste Not: Meta-Embedding of Word and Context Vectors</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1007/978-3-030-23281-8_35</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <controlfield tag="001">68991</controlfield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-tubitak-destekli-proje-yayinlari</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">The word2vec and fastText models train two vectors per word: a word and a context vector. Typically the context vectors are discarded after training, even though they may contain useful information for different NLP tasks. Therefore we combine word and context vectors in the framework of meta-embeddings. Our experiments show performance increases at several NLP tasks such as text classification, semantic similarity, and analogy. In conclusion, this approach can be used to increase performance at downstream tasks while requiring minimal additional computational resources.</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="2">opendefinition.org</subfield>
    <subfield code="a">cc-by</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Marmara Univ, TR-34730 Istanbul, Turkey</subfield>
    <subfield code="a">Gerek, Aydin</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Marmara Univ, TR-34730 Istanbul, Turkey</subfield>
    <subfield code="a">Ganiz, Murat Can</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="b">conferencepaper</subfield>
    <subfield code="a">publication</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Marmara Univ, TR-34730 Istanbul, Turkey</subfield>
    <subfield code="a">Degirmenci, Selin</subfield>
  </datafield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="a">NATURAL LANGUAGE PROCESSING AND INFORMATION SYSTEMS (NLDB 2019)</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-01-01</subfield>
  </datafield>
  <controlfield tag="005">20210316025544.0</controlfield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="o">oai:zenodo.org:68991</subfield>
    <subfield code="p">user-tubitak-destekli-proje-yayinlari</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="z">md5:cf9b014298a06ef4b655bddbc09b965c</subfield>
    <subfield code="s">164</subfield>
    <subfield code="u">https://aperta.ulakbim.gov.trrecord/68991/files/bib-25a74055-4dd9-4f9c-8285-06384aa7ecdf.txt</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">http://www.opendefinition.org/licenses/cc-by</subfield>
    <subfield code="a">Creative Commons Attribution</subfield>
  </datafield>
</record>
37
6
görüntülenme
indirilme
Görüntülenme 37
İndirme 6
Veri hacmi 984 Bytes
Tekil görüntülenme 36
Tekil indirme 6

Alıntı yap