Inductive Entity Typing Alignment

Aligning named entity taxonomies for comparing or combining di↵erent named entity extraction systems is a di cult task. Often taxonomies are mapped manually onto each other or onto a standardized ontology but at the loss of subtleties between di↵erent class extensions and domain specific uses of the taxonomy. In this paper, we present an approach and experiments for learning customized taxonomy alignments between di↵erent entity extractors for di↵erent domains. Our inductive data-driven approach recasts the alignment problem as a classification problem. We present experiments on two named entity recognition benchmark datasets, namely the CoNLL2003 newswire dataset and the MSM2013 microposts dataset. Our results show that the automatically induced mappings outperform manual alignments and are agnostic to changes in the extractor taxonomies, implying that alignments are highly contextual.