Solving Hard Coreference Problems
This addresses a key bottleneck in natural language understanding for applications like text analysis, though it is incremental as it builds on existing coreference methods.
The paper tackles the problem of resolving hard pronoun coreference cases, which require deep language understanding, by introducing Predicate Schemas and a constrained optimization framework, achieving significant improvements in state-of-the-art performance on Winograd-style cases while maintaining performance on standard datasets.
Coreference resolution is a key problem in natural language understanding that still escapes reliable solutions. One fundamental difficulty has been that of resolving instances involving pronouns since they often require deep language understanding and use of background knowledge. In this paper, we propose an algorithmic solution that involves a new representation for the knowledge required to address hard coreference problems, along with a constrained optimization framework that uses this knowledge in coreference decision making. Our representation, Predicate Schemas, is instantiated with knowledge acquired in an unsupervised way, and is compiled automatically into constraints that impact the coreference decision. We present a general coreference resolution system that significantly improves state-of-the-art performance on hard, Winograd-style, pronoun resolution cases, while still performing at the state-of-the-art level on standard coreference resolution datasets.