Making Non-Normalized Content Retrievable – A Tagging Pipeline for a Corpus of Expert-Layperson Texts

Volltext-Downloads (blau) und Frontdoor-Views (grau)

Schließen

Conventional terminology resources reach their limits when it comes to automatic content classification of texts in the domain of expertlayperson communication. This can be attributed to the fact that (non-normalized) language usage does not necessarily reflect the terminological elements stored in such resources. We present several strategies to extend a terminological resource with term-related elements in order to optimize automatic content classification of expert-layperson texts.

Metadaten
Author:	Christian Lang GND, Ngoc Duyen Tanja Tu ORCiD GND, Laura Zeidler
URN:	urn:nbn:de:bsz:mh39-121941
DOI:	https://doi.org/https://doi.org/10.34619/srmk-injj
ISBN:	978-989-54081-5-3
Parent Title (English):	Language, Data and Knowledge 2023 (LDK 2023): Proceedings of the 4th Conference on Language, Data and Knowledge
Publisher:	NOVA FCSH - CLUNL
Place of publication:	Portugal
Editor:	Sara CarvalhoORCiD, Anas Fahad KhanORCiD, Ana Ostroški AnićORCiD GND, Blerina SpahiuORCiD, Jorge GraciaORCiD GND, John P. McCraeORCiD GND, Dagmar GromannORCiD, Barbara HeinischORCiD GND, Ana SalgadoORCiD
Document Type:	Part of a Book
Language:	English
Year of first Publication:	2023
Date of Publication (online):	2023/10/23
Publishing Institution:	Leibniz-Institut für Deutsche Sprache (IDS)
Publicationstate:	Veröffentlichungsversion
Reviewstate:	Peer-Review
GND Keyword:	Experte; Kommunikation; Laie; Sprachgebrauch; Terminologie; Text
First Page:	239
Last Page:	244
DDC classes:	400 Sprache / 400 Sprache, Linguistik
Open Access?:	ja
BDSL-Classification:	Grammatik
Leibniz-Classification:	Sprache, Linguistik
Linguistics-Classification:	Grammatikforschung
Program areas:	G2: Sprachinformationssysteme
Licence (English):	Creative Commons - Attribution 4.0 International

Open Access