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

Deep learning for free indirect representation

  • In this paper, we present our work-inprogress to automatically identify free indirect representation (FI), a type of thought representation used in literary texts. With a deep learning approach using contextual string embeddings, we achieve f1 scores between 0.45 and 0.5 (sentence-based evaluation for the FI category) on two very different German corpora, a clear improvement on earlier attempts for this task. We show how consistently marked direct speech can help in this task. In our evaluation, we also consider human inter-annotator scores and thus address measures of certainty for this difficult phenomenon.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar


Author:Annelen BrunnerGND, Ngoc Duyen Tanja TuORCiDGND, Lukas Weimer, Fotis Jannidis
Parent Title (English):Preliminary proceedings of the 15th Conference on Natural Language Processing (KONVENS 2019), October 9 – 11, 2019 at Friedrich-Alexander-Universität Erlangen-Nürnberg
Publisher:German Society for Computational Linguistics & Language Technology und Friedrich-Alexander-Universität Erlangen-Nürnberg
Place of publication:München [u.a.]
Document Type:Conference Proceeding
Year of first Publication:2019
Date of Publication (online):2019/10/15
GND Keyword:Automatische Sprachanalyse; Deutsch; Erlebte Rede; Indirekte Rede; Korpus <Linguistik>
First Page:241
Last Page:245
DDC classes:400 Sprache / 400 Sprache, Linguistik
Open Access?:ja
Leibniz-Classification:Sprache, Linguistik
Program areas:Lexik
Licence (German):License LogoCreative Commons - CC BY-NC-SA - Namensnennung - Nicht kommerziell - Weitergabe unter gleichen Bedingungen 4.0 International