Pair-Linking for Collective Entity Disambiguation: Two Could Be Better Than All

Collective entity disambiguation, or collective entity linking aims to jointly resolve multiple mentions by linking them to their associated entities in a knowledge base. Previous works largely based on the underlying assumption that entities within the same document are highly related. However, the extend to which these mentioned entities are actually connected in reality is rarely studied and therefore raises interesting research questions. For the first time, this paper shows that the semantic relationships between mentioned entities within documents are in fact less dense than expected. This could be attributed to several reasons such as noise, data sparsity and knowledge base incompleteness. As a remedy, we introduces MINTREE, a new tree-based objective for the problem of entity disambiguation. The key intuition behind MINTREE is the concept of coherence relaxation which utilizes the weight of a minimum spanning tree to measure the coherence between entities. Based on this new objective, we devise a novel iterative solution for MINTREE optimization problem which we call Pair-Linking. The idea of Pair-Linking is simple: instead of considering all the given mentions, Pair-Linking iteratively selects the pair with highest confidence at each step for decision making. Via extensive experiments on 8 publicly available benchmark datasets, we show that our approach is not only more accurate but also surprisingly faster than many state-of-the-art collective linking algorithms.