@inproceedings{scheible2025_108290,
  title = {Model Architectures for Quotation Detection},
  author = {Scheible, Christian and Klinger, Roman and Padó, Sebastian},
  year = {2025},
  pages = {1736-1745},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-1082909},
  url = {https://fis.uni-bamberg.de/handle/uniba/108290},
  language = {eng},
  abstract = {Quotation detection is the task of locating spans of quoted speech in text. The state of the art treats this problem as a sequence labeling task and employs linear-chain conditional random fields. We question the efficacy of this choice: The Markov assumption in the model prohibits it from making joint decisions about the begin, end, and internal context of a quotation. We perform an extensive analysis with two new model architectures. We find that (a), simple boundary classification combined with a greedy prediction strategy is competitive with the state of the art; (b), a semi-Markov model significantly outperforms all others, by relaxing the Markov assumption.},
  keywords = {Model Architectures}
}
