Improving Coreference Resolution by Learning Entity-Level Distributed Representations

ACL 2016  ·  Kevin Clark, Christopher D. Manning ·

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. The system substantially outperforms the current state-of-the-art on the English and Chinese portions of the CoNLL 2012 Shared Task dataset despite using few hand-engineered features.

PDF Abstract ACL 2016 PDF ACL 2016 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Coreference Resolution OntoNotes NN Cluster Ranker F1 65.29 # 25

Methods


No methods listed for this paper. Add relevant methods here