Conference paper Open Access

Character-based Neural Embeddings for Tweet Clustering

Nixon, Lyndon; Vakulenko, Svitlana; Lupu, Mihai


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.582565</identifier>
  <creators>
    <creator>
      <creatorName>Nixon, Lyndon</creatorName>
      <givenName>Lyndon</givenName>
      <familyName>Nixon</familyName>
      <affiliation>MODUL Technology</affiliation>
    </creator>
    <creator>
      <creatorName>Vakulenko, Svitlana</creatorName>
      <givenName>Svitlana</givenName>
      <familyName>Vakulenko</familyName>
      <affiliation>Vienna University of Economics and Business</affiliation>
    </creator>
    <creator>
      <creatorName>Lupu, Mihai</creatorName>
      <givenName>Mihai</givenName>
      <familyName>Lupu</familyName>
      <affiliation>TU Wien</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Character-based Neural Embeddings for Tweet Clustering</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2017</publicationYear>
  <subjects>
    <subject>Story Detection, Tweet Clustering, Tweet2vec, Vector Space Model, Character-based Embedding</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2017-04-03</date>
  </dates>
  <resourceType resourceTypeGeneral="Text">Conference paper</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/582565</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/invid-h2020</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="http://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;In this paper we show how the performance of tweet clustering can be improved by leveraging character-based neural networks. The proposed approach overcomes the limitations related to the vocabulary explosion in the word-based models and allows for the seamless processing of the multilingual content. Our evaluation results and code are available on-line.&lt;/p&gt;</description>
  </descriptions>
</resource>
26
17
views
downloads
All versions This version
Views 2626
Downloads 1717
Data volume 3.2 MB3.2 MB
Unique views 2626
Unique downloads 1717

Share

Cite as