Using Type Information to Improve Entity Coreference Resolution
This work addresses coreference resolution for discourse analysis, but it is incremental as it builds on existing neural approaches by adding type information.
The paper tackled coreference resolution by introducing the first neural model that leverages external type information, demonstrating modest accuracy gains using either gold standard or predicted types across four benchmark corpora.
Coreference resolution (CR) is an essential part of discourse analysis. Most recently, neural approaches have been proposed to improve over SOTA models from earlier paradigms. So far none of the published neural models leverage external semantic knowledge such as type information. This paper offers the first such model and evaluation, demonstrating modest gains in accuracy by introducing either gold standard or predicted types. In the proposed approach, type information serves both to (1) improve mention representation and (2) create a soft type consistency check between coreference candidate mentions. Our evaluation covers two different grain sizes of types over four different benchmark corpora.