@inproceedings{BrunnerTuWeimeretal.2019,
  author    = {Annelen Brunner and Ngoc Duyen Tanja Tu and Lukas Weimer and Fotis Jannidis},
  title     = {Deep learning for free indirect representation},
  series = {Preliminary proceedings of the 15th Conference on Natural Language Processing (KONVENS 2019), October 9 – 11, 2019 at Friedrich-Alexander-Universit{\"a}t Erlangen-N{\"u}rnberg},
  publisher = {German Society for Computational Linguistics \& Language Technology und Friedrich-Alexander-Universit{\"a}t Erlangen-N{\"u}rnberg},
  address   = {M{\"u}nchen [u.a.]},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-93151},
  pages     = {241 -- 245},
  year      = {2019},
  abstract  = {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.},
  language  = {en}
}