Chinese NER with Height-Limited Constituent Parsing

Abstract

In this paper, we investigate how to improve Chinese named entity recognition (NER) by jointly modeling NER and constituent parsing, in the framework of neural conditional random fields (CRF). We reformulate the parsing task to heightlimited constituent parsing, by which the computational complexity can be significantly reduced, and the majority of phrase-level grammars are retained. Specifically, an unified model of neural semi-CRF and neural tree-CRF is proposed, which simultaneously conducts word segmentation, part-ofspeech (POS) tagging, NER, and parsing. The challenge comes from how to train and infer the joint model, which has not been solved previously. We design a dynamic programming algorithm for both training and inference, whose complexity is O(n·4h), where n is the sentence length and h is the height limit. In addition, we derive a pruning algorithm for the joint model, which further prunes 99.9% of the search space with 2% loss of the ground truth data. Experimental results on the OntoNotes 4.0 dataset have demonstrated that the proposed model outperforms the state-of-the-art method by 2.79 points in the F1-measure.