Document Type
Article
Publication Date
2014
Abstract
We propose a novel search-based approach for greedy coreference resolution, where the mentions are processed in order and added to previous coreference clusters. Our method is distinguished by the use of two functions to make each coreference decision: a pruning function that prunes bad coreference decisions from further consideration, and a scoring function that then selects the best among the remaining decisions. Our framework reduces learning of these functions to rank learning, which helps leverage powerful off-the-shelf rank-learners. We show that our Prune-and-Score approach is superior to using a single scoring function to make both decisions and outperforms several state-of-the-art approaches on multiple benchmark corpora including OntoNotes
Recommended Citation
Ma, Chao; Doppa, Janardhan Rao; Orr, J. Walker; Mannem, Prashanth; Fern, Xiaoli; Dietterich, Tom; and Tadepalli, Prasad, "Prune-and-Score: Learning for Greedy Coreference Resolution" (2014). Faculty Publications - Department of Electrical Engineering and Computer Science. 50.
https://digitalcommons.georgefox.edu/eecs_fac/50
Comments
Originally published in Ma, C., Rao Doppa, J., Orr, J., Fern, M., Dietterich, T., & Tadepalli, P. (2014). Prune-and-Score: Learning for Greedy Coreference Resolution (pp. 2115–2126). https://aclanthology.org/D14-1225.pdf