Coreference Resolution On Conll 2012

Métriques

Avg F1

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
Maverick_mes	83.6	Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends
seq2seq	83.3	Coreference Resolution through a seq2seq Transition-Based System
CorefQA + SpanBERT-large	83.1	CorefQA: Coreference Resolution as Query-based Span Prediction
ASP+T0-3B	82.3	Autoregressive Structured Prediction with Language Models
wl-coref + RoBERTa	81.0	Word-Level Coreference Resolution
s2e + Longformer-Large	80.3	Coreference Resolution without Span Representations
c2f + SpanBERT-Large	80.2	Coreference Resolution without Span Representations
SpanBERT + Cluster Merging	80.2	Revealing the Myth of Higher-Order Inference in Coreference Resolution
CorefQA + SpanBERT-base	79.9	CorefQA: Coreference Resolution as Query-based Span Prediction
U-MEM* + SpanBERT-large	79.6	Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks
c2f-coref + BERT-large	76.9	BERT for Coreference Resolution: Baselines and Analysis
EE + BERT-large	76.61	Coreference Resolution with Entity Equalization
dali-full-anaphora	76.4	A Cluster Ranking Model for Full Anaphora Resolution
reinforced model + ELMO	73.8	End-to-end Deep Reinforcement Learning Based Coreference Resolution
c2f-coref + ELMo	73.0	Higher-order Coreference Resolution with Coarse-to-fine Inference
e2e-coref + ELMo	70.4	End-to-end Neural Coreference Resolution
e2e-coref (ensemble)	68.8	End-to-end Neural Coreference Resolution
e2e-coref (single)	67.2	End-to-end Neural Coreference Resolution

0 of 18 row(s) selected.

Coreference Resolution On Conll 2012 | SOTA | HyperAI