Word Sense Disambiguation On Words In Context

Metrics

Accuracy

Results

Performance results of various models on this benchmark

		Paper Title	Repository
COSINE + Transductive Learning	85.3	Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach
PaLM 540B (finetuned)	78.8	PaLM: Scaling Language Modeling with Pathways
ST-MoE-32B 269B (fine-tuned)	77.7	ST-MoE: Designing Stable and Transferable Sparse Expert Models
DeBERTa-Ensemble	77.5	DeBERTa: Decoding-enhanced BERT with Disentangled Attention
Vega v2 6B (fine-tuned)	77.4	Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE	-
UL2 20B (fine-tuned)	77.3	UL2: Unifying Language Learning Paradigms
Turing NLR v5 XXL 5.4B (fine-tuned)	77.1	Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE	-
T5-XXL 11B	76.9	Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
DeBERTa-1.5B	76.4	DeBERTa: Decoding-enhanced BERT with Disentangled Attention
ST-MoE-L 4.1B (fine-tuned)	74	ST-MoE: Designing Stable and Transferable Sparse Expert Models
SenseBERT-large 340M	72.1	SenseBERT: Driving Some Sense into BERT	-
SenseBERT-base 110M	70.3	SenseBERT: Driving Some Sense into BERT	-
PaLM 2-L (one-shot)	66.8	PaLM 2 Technical Report
BERT-large 340M	65.5	WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations	-
FLAN-T5-Large 783M	64.7	LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions
LaMini-F-T5 783M	63.8	LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions
Context2vec	59.3	WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations	-
DeConf	58.7	WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations	-
SW2V	58.1	WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations	-
ElMo	57.7	WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations	-

0 of 37 row(s) selected.

Command Palette

Word Sense Disambiguation On Words In Context

Metrics

Results