Joint Neural Entity Disambiguation with Output Space Search
This addresses entity disambiguation in natural language processing, which is incremental as it builds on existing local models with global search enhancements.
The paper tackles entity disambiguation by combining local contextual information with global evidence using Limited Discrepancy Search, starting from a local model solution and refining it through heuristic-guided corrections. Experimental results on CoNLL 2003 and TAC 2010 benchmarks show the model's effectiveness, though no specific numerical improvements are provided.
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.