End-to-end Neural Coreference Resolution

EMNLP 2017 Kenton LeeLuheng HeMike LewisLuke Zettlemoyer

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. The key idea is to directly consider all spans in a document as potential mentions and learn distributions over possible antecedents for each... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Coreference Resolution CoNLL 2012 Lee et al. (2017) (single) Avg F1 67.2 # 3
Coreference Resolution CoNLL 2012 Lee et al. (2017) (ensemble) Avg F1 68.8 # 2
Coreference Resolution CoNLL 2012 Lee et al. (2017) + ELMo Avg F1 70.4 # 1
Coreference Resolution OntoNotes e2e-coref F1 67.2 # 10

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet