Abstract
We present a global joint model for lemmatization and part-of-speech prediction. Using only morphological lexicons and unlabeled data, we learn a partiallysupervised part-of-speech tagger and a lemmatizer which are combined using features on a dynamically linked dependency structure of words. We evaluate our model on English, Bulgarian, Czech, and Slovene, and demonstrate substantial improvements over both a direct transduction approach to lemmatization and a pipelined approach, which predicts part-of-speech tags before lemmatization. © 2009 ACL and AFNLP.
Cite
CITATION STYLE
Toutanova, K., & Cherry, C. (2009). A global model for joint lemmatization and part-of-speech prediction. In ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf. (pp. 486–494). https://doi.org/10.3115/1687878.1687947
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
