Improving Coreference Resolution by Learning Entity-Level Distributed Representations

Understand

A long-standing challenge in coreference resolution has been the incorporation of entity-level information - features defined over clusters of mentions instead of mention pairs.

• We present a neural network based coreference system that produces high-dimensional vector representations for pairs of coreference clusters.
• Using these representations, our system learns when combining clusters is desirable.
• We train the system with a learning-to-search algorithm that teaches it which local decisions (cluster merges) will lead to a high-scoring final coreference partition.