Conference paper Open Access

A Case Study of Closed-Domain Response Suggestion with Limited Training Data

Galke, Lukas; Gerstenkorn, Gunnar; Scherp, Ansgar


Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Galke, Lukas</dc:creator>
  <dc:creator>Gerstenkorn, Gunnar</dc:creator>
  <dc:creator>Scherp, Ansgar</dc:creator>
  <dc:date>2018-09-06</dc:date>
  <dc:description>We analyze the problem of response suggestion in a closed domain along a real-world scenario of a digital library. We present a text-processing pipeline to generate question-answer pairs from chat transcripts. On this limited amount of training data, we compare retrieval-based, conditioned-generation, and dedicated representation learning approaches for response suggestion. Our results show that retrieval-based methods that strive to find similar, known contexts are preferable over parametric approaches from the conditioned-generation family, when the training data is limited. We, however, identify a specific representation learning approach that is competitive to the retrieval-based approaches despite the training data limitation.</dc:description>
  <dc:identifier>https://zenodo.org/record/2583130</dc:identifier>
  <dc:identifier>10.1007/978-3-319-99133-7_18</dc:identifier>
  <dc:identifier>oai:zenodo.org:2583130</dc:identifier>
  <dc:language>eng</dc:language>
  <dc:relation>info:eu-repo/grantAgreement/EC/H2020/693092/</dc:relation>
  <dc:relation>url:https://zenodo.org/communities/moving-h2020</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:rights>http://creativecommons.org/licenses/by/4.0/legalcode</dc:rights>
  <dc:subject>conversational agents</dc:subject>
  <dc:subject>neural networks</dc:subject>
  <dc:subject>representation learning</dc:subject>
  <dc:title>A Case Study of Closed-Domain Response Suggestion with Limited Training Data</dc:title>
  <dc:type>info:eu-repo/semantics/conferencePaper</dc:type>
  <dc:type>publication-conferencepaper</dc:type>
</oai_dc:dc>
17
20
views
downloads
Views 17
Downloads 20
Data volume 4.7 MB
Unique views 15
Unique downloads 18

Share

Cite as