End-to-end Neural Coreference Resolution

@article{Lee2017EndtoendNC,
  title={End-to-end Neural Coreference Resolution},
  author={Kenton Lee and Luheng He and Mike Lewis and Luke Zettlemoyer},
  journal={ArXiv},
  year={2017},
  volume={abs/1707.07045}
}
Highlight Information
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 hand-engineered mention detector. [...] Key Method The model computes span embeddings that combine context-dependent boundary representations with a head-finding attention mechanism. It is trained to maximize the marginal likelihood of gold antecedent spans from coreference clusters and is factored to enable aggressive pruning of potential mentions…Expand Abstract

Citations

Publications citing this paper.
SHOWING 1-10 OF 208 CITATIONS

4 Mind the GAP : A Balanced Corpus of Gendered Ambiguous Pronouns

VIEW 6 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

An Annotated Dataset of Coreference in English Literature

VIEW 7 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Coreference Resolution as Query-based Span Prediction

VIEW 16 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Ellipsis and Coreference Resolution as Question Answering

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Improving Generalization in Coreference Resolution via Adversarial Training

VIEW 10 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

Incorporating Structural Information for Better Coreference Resolution

VIEW 9 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Neural Mention Detection

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Spoken Conversational Search for General Knowledge

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Study on Improving End-to-End Neural Coreference Resolution

VIEW 13 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2020

CITATION STATISTICS

  • 43 Highly Influenced Citations

  • Averaged 67 Citations per year from 2017 through 2019

  • 80% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 16 REFERENCES

Learning Global Features for Coreference Resolution

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

A Joint Model for Entity Analysis: Coreference, Typing, and Linking