FANDOM



Bohnet & Nivre (2012)[1]: "We present a transition-based system for joint part-of-speech tagging and labeled dependency parsing with non-projective trees. Experimental evaluation on Chinese, Czech, English and German shows consistent improvements in both tagging and parsing accuracy when compared to a pipeline system [...] best parsers based on PCFG models, such as the Brown parser (Charniak and Johnson, 2005) and the Berkeley parser (Petrov et al., 2006; Petrov and Klein, 2007), which not only can perform their own part-of-speech tagging but normally give better parsing accuracy when they are allowed to do so. [...] Lee et al. (2011) show that a discriminative model for joint morphological disambiguation and dependency parsing out- performs a pipeline model in experiments on Latin, Ancient Greek, Czech and Hungarian. However, Li et al. (2011) and Hatori et al. (2011) report improvements with a joint model also for Chinese [...] "

Chinese: Li et al. (2011)[2], Li et al. (2014)[3], word segmentation+POS tagging+parsing: Qian & Liu (2012)[4].

References Edit

  1. Bohnet, B., & Nivre, J. (2012, July). A transition-based system for joint part-of-speech tagging and labeled non-projective dependency parsing. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (pp. 1455-1465). Association for Computational Linguistics.
  2. Li, Z., Zhang, M., Che, W., Liu, T., Chen, W., & Li, H. (2011, July). Joint models for Chinese POS tagging and dependency parsing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (pp. 1180-1191). Association for Computational Linguistics.
  3. Li, Z., Zhang, M., Che, W., Liu, T., & Chen, W. (2014). Joint Optimization for Chinese POS Tagging and Dependency Parsing. Audio, Speech, and Language Processing, IEEE/ACM Transactions on, 22(1), 274-286.
  4. Qian, X., & Liu, Y. (2012, July). Joint Chinese word segmentation, POS tagging and parsing. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (pp. 501-511). Association for Computational Linguistics.