Please use this identifier to cite or link to this item: http://hdl.handle.net/1893/27857
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGalke, Lukasen_UK
dc.contributor.authorGerstenkorn, Gunnaren_UK
dc.contributor.authorScherp, Ansgaren_UK
dc.contributor.editorElloumi, Men_UK
dc.contributor.editorGranitzer, Men_UK
dc.contributor.editorHameurlain, Aen_UK
dc.contributor.editorSeifert, Cen_UK
dc.contributor.editorStein, Ben_UK
dc.contributor.editorTjoa, AMen_UK
dc.contributor.editorWagner, Ren_UK
dc.date.accessioned2018-09-27T14:34:12Z-
dc.date.available2018-09-27T14:34:12Z-
dc.date.issued2018-12-31en_UK
dc.identifier.urihttp://hdl.handle.net/1893/27857-
dc.description.abstractWe 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.en_UK
dc.language.isoenen_UK
dc.publisherSpringer International Publishingen_UK
dc.relationGalke L, Gerstenkorn G & Scherp A (2018) A Case Study of Closed-Domain Response Suggestion with Limited Training Data. In: Elloumi M, Granitzer M, Hameurlain A, Seifert C, Stein B, Tjoa A & Wagner R (eds.) Database and Expert Systems Applications. DEXA 2018. Communications in Computer and Information Science, 903. DEXA 2018: International Conference on Database and Expert Systems Applications, 03.09.2018-06.09.2018. Cham, Switzerland: Springer International Publishing, pp. 218-229. https://doi.org/10.1007/978-3-319-99133-7_18en_UK
dc.relation.ispartofseriesCommunications in Computer and Information Science, 903en_UK
dc.rightsThis is a post-peer-review, pre-copyedit version of a paper published in Elloumi M, Granitzer M, Hameurlain A, Seifert C, Stein B, Tjoa A & Wagner R (eds.) Database and Expert Systems Applications. DEXA 2018. Communications in Computer and Information Science, 903. The final authenticated version is available online at: https://doi.org/10.1007/978-3-319-99133-7_18en_UK
dc.titleA Case Study of Closed-Domain Response Suggestion with Limited Training Dataen_UK
dc.typeConference Paperen_UK
dc.identifier.doi10.1007/978-3-319-99133-7_18en_UK
dc.citation.issn1865-0937en_UK
dc.citation.issn1865-0929en_UK
dc.citation.spage218en_UK
dc.citation.epage229en_UK
dc.citation.publicationstatusPublisheden_UK
dc.type.statusAM - Accepted Manuscripten_UK
dc.contributor.funderEuropean Commissionen_UK
dc.citation.btitleDatabase and Expert Systems Applications. DEXA 2018en_UK
dc.citation.conferencedates2018-09-03 - 2018-09-06en_UK
dc.citation.conferencenameDEXA 2018: International Conference on Database and Expert Systems Applicationsen_UK
dc.citation.date07/08/2018en_UK
dc.citation.isbn9783319991320; 9783319991337en_UK
dc.publisher.addressCham, Switzerlanden_UK
dc.contributor.affiliationUniversity of Kielen_UK
dc.contributor.affiliationUniversity of Potsdamen_UK
dc.contributor.affiliationMathematicsen_UK
dc.identifier.scopusid2-s2.0-85051961535en_UK
dc.identifier.wtid972871en_UK
dc.contributor.orcid0000-0001-6124-1092en_UK
dc.contributor.orcid0000-0002-4889-511Xen_UK
dc.contributor.orcid0000-0002-2653-9245en_UK
dc.date.accepted2018-05-18en_UK
dc.date.filedepositdate2018-09-27en_UK
Appears in Collections:Computing Science and Mathematics Book Chapters and Sections

Files in This Item:
File Description SizeFormat 
W42-GalkeEtAl-A Case Study of Closed-Domain Response Suggestion with Limited Training Data.pdfFulltext - Accepted Version255.49 kBAdobe PDFView/Open


This item is protected by original copyright



Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

If you believe that any material held in STORRE infringes copyright, please contact library@stir.ac.uk providing details and we will remove the Work from public display in STORRE and investigate your claim.