Unsupervised Ranking Model for Entity Coreference Resolution
Preprint
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%.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Latent Structures for Coreference ResolutionTransactions of the Association for Computational Linguistics, 2015
- Learning Structured Perceptrons for Coreference Resolution with Latent Antecedents and Non-local Features2014
- Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked RulesComputational Linguistics, 2013
- Unsupervised learning of narrative schemas and their participants2009
- A Twin-Candidate Model for Learning-Based Anaphora ResolutionComputational Linguistics, 2008
- Unsupervised models for coreference resolution2008
- On coreference resolution performance metrics2005
- A Machine Learning Approach to Coreference Resolution of Noun PhrasesComputational Linguistics, 2001