Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Natural Language Processing
/
Word Sense Disambiguation
/
Supervised:
Word Sense Disambiguation on Supervised:
Metric: Senseval 3 (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
Sort:
Senseval 3 (best first)
Senseval 3 (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
Senseval 3
▼
Extra Data
Paper
Date
↕
Code
1
SANDWiCH
85.7
No
SANDWiCH: Semantical Analysis of Neighbours for ...
2025-03-07
Code
2
GlossGPT
82.9
No
-
-
Code
3
ConSeC+WNGC
81
No
-
-
Code
4
ESR+WNGC
80.2
No
-
-
Code
5
ConSeC
79.9
No
-
-
Code
6
ESR
79.9
No
-
-
Code
7
EWISER+WNGC
79
No
-
-
Code
8
EWISER
78.4
No
-
-
Code
9
ESCHER SemCor
77.8
No
-
-
Code
10
SemCor+WNGC, hypernyms
77.8
No
Sense Vocabulary Compression through the Semanti...
2019-05-14
Code
11
SparseLMMS
77.8
No
-
-
-
12
BEM
77.4
No
-
-
-
13
SparseLMMS+WNGC
77.3
No
-
-
-
14
ARES
77.1
No
-
-
-
15
GlossBERT
75.2
No
GlossBERT: BERT for Word Sense Disambiguation wi...
2019-08-20
Code
16
BERT (linear projection)
73.6
No
Improved Word Sense Disambiguation Using Pre-Tra...
2019-10-01
Code
17
BERT (nearest neighbour)
71.6
No
Improved Word Sense Disambiguation Using Pre-Tra...
2019-10-01
Code
18
supWSD<sub>emb</sub>
70.6
No
-
-
-
19
GAS<sub>ext</sub>
70.5
No
Incorporating Glosses into Neural Word Sense Dis...
2018-05-21
Code
20
SemCor+WNGT, vocabulary reduced, ensemble
70.11
No
Improving the Coverage and the Generalization Ab...
2018-11-02
-
21
GAS
70
No
Incorporating Glosses into Neural Word Sense Dis...
2018-05-21
Code
22
ELMo
69.6
No
Deep contextualized word representations
2018-02-15
Code
23
Bi-LSTM<sub>att+LEX</sub>
69.4
No
-
-
-
24
Bi-LSTM<sub>att+LEX+POS</sub>
69.1
No
-
-
-
25
context2vec
69.1
No
-
-
-
26
supWSD
68.8
No
-
-
-
27
MFS baseline
66
No
-
-
-
#1
SANDWiCH
SOTA
85.7
Senseval 3
· 2025-03-07
SANDWiCH: Semantical Analysis of Neighbours for Disambiguating Words in Context ad Hoc
Code
#2
GlossGPT
82.9
Senseval 3
No paper
Code
#3
ConSeC+WNGC
81
Senseval 3
No paper
Code
#4
ESR+WNGC
80.2
Senseval 3
No paper
Code
#5
ConSeC
79.9
Senseval 3
No paper
Code
#6
ESR
79.9
Senseval 3
No paper
Code
#7
EWISER+WNGC
79
Senseval 3
No paper
Code
#8
EWISER
78.4
Senseval 3
No paper
Code
#9
ESCHER SemCor
77.8
Senseval 3
No paper
Code
#10
SemCor+WNGC, hypernyms
SOTA
77.8
Senseval 3
· 2019-05-14
Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation
Code
#11
SparseLMMS
77.8
Senseval 3
No paper
#12
BEM
77.4
Senseval 3
No paper
#13
SparseLMMS+WNGC
77.3
Senseval 3
No paper
#14
ARES
77.1
Senseval 3
No paper
#15
GlossBERT
75.2
Senseval 3
· 2019-08-20
GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge
Code
#16
BERT (linear projection)
73.6
Senseval 3
· 2019-10-01
Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations
Code
#17
BERT (nearest neighbour)
71.6
Senseval 3
· 2019-10-01
Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations
Code
#18
supWSD<sub>emb</sub>
70.6
Senseval 3
No paper
#19
GAS<sub>ext</sub>
SOTA
70.5
Senseval 3
· 2018-05-21
Incorporating Glosses into Neural Word Sense Disambiguation
Code
#20
SemCor+WNGT, vocabulary reduced, ensemble
70.11
Senseval 3
· 2018-11-02
Improving the Coverage and the Generalization Ability of Neural Word Sense Disambiguation through Hypernymy and Hyponymy Relationships
#21
GAS
70
Senseval 3
· 2018-05-21
Incorporating Glosses into Neural Word Sense Disambiguation
Code
#22
ELMo
SOTA
69.6
Senseval 3
· 2018-02-15
Deep contextualized word representations
Code
#23
Bi-LSTM<sub>att+LEX</sub>
69.4
Senseval 3
No paper
#24
Bi-LSTM<sub>att+LEX+POS</sub>
69.1
Senseval 3
No paper
#25
context2vec
69.1
Senseval 3
No paper
#26
supWSD
68.8
Senseval 3
No paper
#27
MFS baseline
66
Senseval 3
No paper