End-to-end Neural Coreference Resolution

Abstract

We introduce the first end-to-end coreference resolution model and show that it significantly outperforms all previous work without using a syntactic parser or handengineered mention detector. The key idea is to directly consider all spans in a document as potential mentions and learn distributions over possible antecedents for each. The model computes span… (More)
View Slides

Topics

8 Figures and Tables

Cite this paper

@inproceedings{Lee2017EndtoendNC, title={End-to-end Neural Coreference Resolution}, author={Kenton Lee and Luheng He and Mike Lewis and Luke S. Zettlemoyer}, booktitle={EMNLP}, year={2017} }