Konferenzbeitrag

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.

Deep learning for free indirect representation

Urheber*in: Brunner, Annelen; Tu, Ngoc Duyen Tanja; Weimer, Lukas; Jannidis, Fotis

Attribution - NonCommercial - ShareAlike 4.0 International

0
/
0

Language
Englisch

Subject
Deutsch
Indirekte Rede
Erlebte Rede
Automatische Sprachanalyse
Korpus <Linguistik>
Sprache

Event
Geistige Schöpfung
(who)
Brunner, Annelen
Tu, Ngoc Duyen Tanja
Weimer, Lukas
Jannidis, Fotis
Event
Veröffentlichung
(who)
München [u.a.] : German Society for Computational Linguistics & Language Technology und Friedrich-Alexander-Universität Erlangen-Nürnberg
(when)
2019-10-15

URN
urn:nbn:de:bsz:mh39-93151
Last update
06.03.2025, 9:00 AM CET

Data provider

This object is provided by:
Leibniz-Institut für Deutsche Sprache - Bibliothek. If you have any questions about the object, please contact the data provider.

Object type

  • Konferenzbeitrag

Associated

  • Brunner, Annelen
  • Tu, Ngoc Duyen Tanja
  • Weimer, Lukas
  • Jannidis, Fotis
  • München [u.a.] : German Society for Computational Linguistics & Language Technology und Friedrich-Alexander-Universität Erlangen-Nürnberg

Time of origin

  • 2019-10-15

Other Objects (12)