Constrained Multi-Task Learning for Bridging Resolution

Abstract

We examine the extent to which supervised bridging resolvers can be improved without employing additional labeled bridging data by proposing a novel constrained multi-task learning framework for bridging resolution, within which we (1) design cross-task consistency constraints to guide the learning process; (2) pre-train the entity coreference model in the multitask framework on the large amount of publicly available coreference data; and (3) integrate prior knowledge encoded in rule-based resolvers. Our approach achieves state-of-the-art results on three standard evaluation corpora.