Higher-order Coreference Resolution with Coarse-to-fine Inference

@inproceedings{Lee2018HigherorderCR,
  title={Higher-order Coreference Resolution with Coarse-to-fine Inference},
  author={Kenton Lee and Luheng He and Luke Zettlemoyer},
  booktitle={NAACL-HLT},
  year={2018}
}
We introduce a fully differentiable approximation to higher-order inference for coreference resolution. [...] Key Method This enables the model to softly consider multiple hops in the predicted clusters. To alleviate the computational cost of this iterative process, we introduce a coarse-to-fine approach that incorporates a less accurate but more efficient bilinear factor, enabling more aggressive pruning without hurting accuracy. Compared to the existing state-of-the-art span-ranking approach, our model…Expand

Paper Mentions

Revealing the Myth of Higher-Order Inference in Coreference Resolution
Coreference Resolution with Entity Equalization
Coreference Resolution without Span Representations
Revisiting Memory-Efficient Incremental Coreference Resolution
End-to-end Deep Reinforcement Learning Based Coreference Resolution
A Study on Improving End-to-End Neural Coreference Resolution
Fast End-to-end Coreference Resolution for Korean
Using Type Information to Improve Entity Coreference Resolution
Adaptive Active Learning for Coreference Resolution
Pre-training of Mention Representations in Coreference Models
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 17 REFERENCES
End-to-end Neural Coreference Resolution
Learning Global Features for Coreference Resolution
Latent Structures for Coreference Resolution
Deep Reinforcement Learning for Mention-Ranking Coreference Models
Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution
Understanding the Value of Features for Coreference Resolution
Specialized Models and Ranking for Coreference Resolution
...
1
2
...