FANDOM


Parsing: Goldberg and Elhadad (Goldberg and Elhadad, 2010)[1] (Tratz and Hovy, 2011[2]; Ma et al., 2012[3]; Ma et al., 2013[4]).

AKA "baby step" approach (Lee et al. 2012)[5]

From Lee et al.: "Our model follows a cautious (or “baby steps”) approach, which we previously showed to be successful for entity coreference resolution (Raghunathan et al., 2010; Lee et al., 2011)."

TODO: overview? Xie et al. (2015)[6]

References Edit

  1. Yoav Goldberg and Michael Elhadad. 2010. An Ef- ficient Algorithm for Easy-First Non-Directional De- pendency Parsing. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter ofthe Association for Computational Linguis- tics, pages 742–750, Los Angeles, California, June. Association for Computational Linguistics.
  2. Stephen Tratz and Eduard Hovy. 2011. A fast, effective, non-projective, semantically-enriched parser. In Proc. ofEMNLP.
  3. Ji Ma, Tong Xiao, Jingbo Zhu, and Feiliang Ren. 2012. Easy-First Chinese POS Tagging and Dependency Parsing. In Proceedings of COLING 2012, pages 1731–1746, Mumbai, India, December. The COLING 2012 Organizing Committee.
  4. Ji Ma, Jingbo Zhu, Tong Xiao, and Nan Yang. 2013. Easy-First POS Tagging and Dependency Parsing with Beam Search. In Proceedings of the 51st Annual Meeting ofthe Association for Computational Linguis- tics (Volume 2: Short Papers), pages 110–114, Sofia, Bulgaria, August. Association for Computational Lin- guistics.
  5. Lee, H., Recasens, M., Chang, A., Surdeanu, M., & Jurafsky, D. (2012). Joint Entity and Event Coreference Resolution across Documents. (EMNLP-CoNLL 2012) Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, (July), 489–500.
  6. Xie, J., Ma, C., Doppa, J. R., Mannem, P., Fern, X. Z., Dietterich, T. G., & Tadepalli, P. (2015). Learning Greedy Policies for the Easy-First Framework. AAAI, 2339–2345. Retrieved from http://dblp.uni-trier.de/db/conf/aaai/aaai2015.html#XieMDMFDT15
Community content is available under CC-BY-SA unless otherwise noted.