Unsupervised Ranking Model for Entity Coreference Resolution
Computation and Language
2016-03-16 v1 Machine Learning
Abstract
Coreference resolution is one of the first stages in deep language understanding and its importance has been well recognized in the natural language processing community. In this paper, we propose a generative, unsupervised ranking model for entity coreference resolution by introducing resolution mode variables. Our unsupervised system achieves 58.44% F1 score of the CoNLL metric on the English data from the CoNLL-2012 shared task (Pradhan et al., 2012), outperforming the Stanford deterministic system (Lee et al., 2013) by 3.01%.
Cite
@article{arxiv.1603.04553,
title = {Unsupervised Ranking Model for Entity Coreference Resolution},
author = {Xuezhe Ma and Zhengzhong Liu and Eduard Hovy},
journal= {arXiv preprint arXiv:1603.04553},
year = {2016}
}
Comments
Accepted by NAACL 2016