Refine
Year of publication
- 2019 (1)
Document Type
Language
- English (1)
Has Fulltext
- yes (1)
Is part of the Bibliography
- yes (1)
Keywords
- Automatische Sprachanalyse (1)
- Deutsch (1)
- Erlebte Rede (1)
- Indirekte Rede (1)
- Korpus <Linguistik> (1)
Publicationstate
Reviewstate
- Peer-Review (1)
Publisher
- German Society for Computational Linguistics & Language Technology und Friedrich-Alexander-Universität Erlangen-Nürnberg (1) (remove)
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.