<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>7093</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>157</pageFirst>
    <pageLast>164</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>TUDpress</publisherName>
    <publisherPlace>Dresden</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Is there Text in Wine? – S+U Learning-based Named Entity Recognition and Triplet Extraction from Wine Aroma Descriptors</title>
    <abstract language="eng">Wine making is usually considered a domain being far off the processing of speech and language. But in a particular aspect, the domains of speech processing and wine making are related, namely, in the description of wine aromas. These descriptors are used for creating wine expertise as well as more general (advertisement-like) textual  representations. In the current paper, we use Natural Language Processing techniques, especially Named Entity Recognition, to identify Aspects and Opinions, reflecting wine characteristics. These are combined with analyses of respective relations (triplet extraction) building Aspect-Opinion-Pairs to establish indicative aroma descriptors, also trying to approach the complex interplay amongst these individual statements. In our experiments, we rely on the Falstaff corpus comprising a huge set of wine descriptions. This results in an average F1 score of around 0.85 for Aspect-Opinion classification. For triplet generation multiple strategies were compared, resulting in an average F1 score of 0.67 in this challenging task. For both tasks we rely only on a handful of manually annotated samples, applying pseudo-labeling methods from seed data to achieve automatic labeling.</abstract>
    <parentTitle language="deu">Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. März 2024</parentTitle>
    <identifier type="doi">10.35096/othr/pub-7093</identifier>
    <identifier type="urn">urn:nbn:de:bvb:898-opus4-70931</identifier>
    <identifier type="isbn">978-3-95908-325-6</identifier>
    <enrichment key="OtherSeries">Studientexte zur Sprachkommunikation ; 107</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Siddarth Venkateswaran</author>
    <author>Abdullah Al Foysal</author>
    <author>Nazeer Basha Shaik</author>
    <author>Ronald Böck</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
    <thesisPublisher>Ostbayerische Technische Hochschule Regensburg</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-oth-regensburg/files/7093/essv2024_157.pdf</file>
  </doc>
</export-example>
