In this paper, we present a novel model for entity disambiguation that combines both local contextual information and global evidences through Limited Discrepancy Search (LDS). Given an input document, we start from a complete solution constructed by a local model and conduct a search in the space of possible corrections to improve the local solution from a global view point. Our search utilizes a heuristic function to focus more on the least confident local decisions and a pruning function to score the global solutions based on their local fitness and the global coherences among the predicted entities. Experimental results on CoNLL 2003 and TAC 2010 benchmarks verify the effectiveness of our model.
@article{arxiv.1806.07495,
title = {Joint Neural Entity Disambiguation with Output Space Search},
author = {Hamed Shahbazi and Xiaoli Z. Fern and Reza Ghaeini and Chao Ma and Rasha Obeidat and Prasad Tadepalli},
journal= {arXiv preprint arXiv:1806.07495},
year = {2019}
}