@article{Brunner2015, author = {Annelen Brunner}, title = {Automatic recognition of speech, thought, and writing representation in German narrative texts}, series = {Literary and Linguistic Computing}, volume = {28}, number = {4}, issn = {1477-4615}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-39470}, pages = {563 -- 575}, year = {2015}, abstract = {This article presents the main results of a project, which explored ways to recognize and classify a narrative feature—speech, thought, and writing representation (ST\&WR)—automatically, using surface information and methods of computational linguistics. The task was to detect and distinguish four types—direct, free indirect, indirect, and reported ST\&WR—in a corpus of manually annotated German narrative texts. Rule-based as well as machine-learning methods were tested and compared. The results were best for recognizing direct ST\&WR (best F1 score: 0.87), followed by indirect (0.71), reported (0.58), and finally free indirect ST\&WR (0.40). The rule-based approach worked best for ST\&WR types with clear patterns, like indirect and marked direct ST\&WR, and often gave the most accurate results. Machine learning was most successful for types without clear indicators, like free indirect ST\&WR, and proved more stable. When looking at the percentage of ST\&WR in a text, the results of machine-learning methods always correlated best with the results of manual annotation. Creating a union or intersection of the results of the two approaches did not lead to striking improvements. A stricter definition of ST\&WR, which excluded borderline cases, made the task harder and led to worse results for both approaches.}, language = {en} }