Model Architectures for Quotation Detection
Scheible, Christian; Klinger, Roman; Padó, Sebastian (2016): Model Architectures for Quotation Detection, in: Katrin Erk, Noah A. Smith, Katrin Erk, u. a. (Hrsg.), Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, S. 1736–1745, doi: 10.18653/v1/P16-1164.
Details
- Fakultät/Lehrstuhl
- Autorin(nen)/Autor(en)
- Scheible, ChristianPadó, Sebastian
- Titel des Sammelwerks
- Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics
- Band/Titel des Bands
- 1, Long Papers
- Herausgeberin(nen)/Herausgeber des Sammelwerks
- Erk, KatrinSmith, Noah A.
- Konferenz
- 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany
- Verlagsangabe
- Association for Computational Linguistics
- Erscheinungsjahr
- 2016
- Sprache(n)
- Englisch
- DOI
- URL
- 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.
- GND-Schlagwort(e)
- Maschinelles LernenZitatenanalyseModell
- Freie Schlagwort(e)
- Model Architectures
- DDC-Klassifikation
- 004 Computer science
- RVK-Klassifikation
- ST 306
- Peer Reviewed
- ja
- Internationale Verbreitung
- ja
- Open-Access-Zeitschrift
- ja
- Dokumenttyp
- Konferenzveröffentlichung
- URI
- Datum der Freischaltung
- 13.03.2024