Coreference Resolution On Ontonotes

평가 지표

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	F1	Paper Title	Repository
e2e-coref	67.2	End-to-end Neural Coreference Resolution	-
Reward Rescaling	65.73	Deep Reinforcement Learning for Mention-Ranking Coreference Models	-
Maverick_mes	83.6	Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends	-
longdoc S (ON + PreCo + LitBank + 30k pseudo-singletons)	79.6	On Generalization in Coreference Resolution	-
longdoc S (OntoNotes + 60k pseudo-singletons)	80.6	On Generalization in Coreference Resolution	-
ASP+T0-3B	82.3	Autoregressive Structured Prediction with Language Models	-
e2e-coref + ELMo + hyperparameter tuning	72.3	Higher-order Coreference Resolution with Coarse-to-fine Inference	-
Reinforced + ELMo	73.8	End-to-end Deep Reinforcement Learning Based Coreference Resolution	-
U-MEM + Longformer	80.9	Efficient and Interpretable Neural Models for Entity Tracking	-
e2e-coref + ELMo	70.4	Deep contextualized word representations	-
NN Cluster Ranker	65.29	Improving Coreference Resolution by Learning Entity-Level Distributed Representations	-
U-MEM* + SpanBERT	79.6	Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks	-
longdoc S (OntoNotes + PreCo + LitBank)	79.2	On Generalization in Coreference Resolution	-
wl-coref + RoBERTa	81	Word-Level Coreference Resolution	-
c2f-coref	73.0	Higher-order Coreference Resolution with Coarse-to-fine Inference	-
G2GT SpanBERT-large overlap	80.2	Graph Refinement for Coreference Resolution	-
E2E-CR + ASL	67.8	Learning Word Representations with Cross-Sentence Dependency for End-to-End Co-reference Resolution
seq2seq	83.3	Coreference Resolution through a seq2seq Transition-Based System	-
SpanBERT	79.6	SpanBERT: Improving Pre-training by Representing and Predicting Spans	-
G2GT SpanBERT-large reduced	80.5	Graph Refinement for Coreference Resolution	-

0 of 26 row(s) selected.