Conference paper Open Access

Multilingual Dynamic Topic Model

Elaine Zosa; Mark Granroth-Wilding


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">Topic modeling</subfield>
  </datafield>
  <controlfield tag="005">20200120171140.0</controlfield>
  <controlfield tag="001">3402878</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">2-4 September 2019</subfield>
    <subfield code="g">RANLP</subfield>
    <subfield code="a">Recent Advances in Natural Language Processing</subfield>
    <subfield code="c">Bulgaria</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Helsinki</subfield>
    <subfield code="a">Mark Granroth-Wilding</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">398196</subfield>
    <subfield code="z">md5:8e76ae0c7dedae0cd23529bfa1f924d9</subfield>
    <subfield code="u">https://zenodo.org/record/3402878/files/multilingual_dynamic_topic_model_granrothwilding_zosa.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">http://lml.bas.bg/ranlp2019/start.php</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-09-02</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o">oai:zenodo.org:3402878</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of Helsinki</subfield>
    <subfield code="a">Elaine Zosa</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Multilingual Dynamic Topic Model</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">770299</subfield>
    <subfield code="a">NewsEye: A Digital Investigator for Historical Newspapers</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;Dynamic topic models (DTMs) capture the evolution of topics and trends in time series data.&lt;br&gt;
Current DTMs are applicable only to monolingual datasets. In this paper we present the multilingual&lt;br&gt;
dynamic topic model (ML-DTM), a novel topic model that combines DTM with an existing multilingual&lt;br&gt;
topic modeling method to capture crosslingual topics that evolve across time. We present&lt;br&gt;
results of this model on a parallel German-English corpus of news articles and a comparable corpus&lt;br&gt;
of Finnish and Swedish news articles. We demonstrate&amp;nbsp;the capability of ML-DTM to track significant&lt;br&gt;
events related to a topic and show that it finds&amp;nbsp;distinct topics and performs as well as existing&lt;br&gt;
multilingual topic models in aligning cross-lingual&amp;nbsp;topics.&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.3402877</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3402878</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
365
444
views
downloads
All versions This version
Views 365365
Downloads 444444
Data volume 176.8 MB176.8 MB
Unique views 321321
Unique downloads 429429

Share

Cite as