Chinese shallow parsing is a difficult, important and widely-studied sequence modeling problem. CRFs are new discriminative sequential models which may incorporate many rich features. This paper shows how conditional random fields (CRFs) can be efficiently applied to Chinese shallow parsing. We employ using CRFs and HMMs on a same data set. Our results confirm that CRFs improve the performance upon HMMs. Our approach yields the F1 score of 90.38% in Chinese shallow parsing with the UPenn Chinese Treebank. CRFs have shown to perform well for Chinese shallow parsing due to their ability to capture arbitrary, overlapping features of the input in a Markov model. © Springer-Verlag Berlin Heidelberg 2005.
CITATION STYLE
Tan, Y., Yao, T., Chen, Q., & Zhu, J. (2005). Applying conditional random fields to Chinese shallow parsing. In Lecture Notes in Computer Science (Vol. 3406, pp. 167–176). Springer Verlag. https://doi.org/10.1007/978-3-540-30586-6_16
Mendeley helps you to discover research relevant for your work.