Our new X account is live! Follow @wizwand_team for updates

Named Entity Recognition on Weibo (test)

70.5Overall Score

SoftLexicon (LSTM) + BERT

Updated 3d ago

Evaluation Results

Method
SoftLexicon (LSTM) + BERT 2019.08	70.5	70.94	67.02	-	-	-
SoftLexicon (LSTM) + BERT 2019.08	70.5	70.94	67.02	-	-	-
BERT + MECT 2021.07	70.43	-	-	-	-	-
BERT 2021.07	68.2	-	-	-	-	-
BERT + LSTM + CRF 2019.08	67.33	69.65	64.62	-	-	-
BERT-Tagger 2019.08	63.8	65.77	62.05	-	-	-
MECT 2021.07	63.3	61.91	62.51	-	-	-
SoftLexicon (LSTM) 2019.08	61.42	59.08	62.22	-	-	-
SoftLexicon (LSTM) 2021.07	61.42	59.08	62.22	-	-	-
Baseline (FLAT) 2021.07	60.32	-	-	-	-	-
LGN 2021.07	60.21	55.34	64.98	-	-	-
LR-CNN 2019.08	59.92	57.14	66.67	-	-	-
LR-CNN 2021.07	59.92	57.14	66.67	-	-	-
SoftLexicon (LSTM) + bichar 2019.08	59.81	58.12	64.2	-	-	-
PLT 2021.07	59.76	53.55	64.9	-	-	-
CAN Model 2019.04	59.31	55.38	62.98	-	-	-
CAN-NER 2021.07	59.31	55.38	62.98	-	-	-
Peng and Dredze [18] 2019.04	58.99	55.28	62.97	-	-	-
Peng and Dredze 2019.08	58.99	55.28	62.97	-	-	-
Peng and Dredze 2021.07	58.99	55.28	62.97	-	-	-
Zhang and Yang [10] 2019.04	58.79	53.04	62.25	-	-	-
Lattice-LSTM 2019.08	58.79	53.04	62.25	-	-	-
Lattice LSTM 2021.07	58.79	53.04	62.25	-	-	-
Cao et al. [11] 2019.04	58.7	51.34	57.35	-	-	-
Cao et al. 2021.07	58.7	54.34	57.35	-	-	-
He and Sun [20] 2019.04	58.23	54.5	62.17	-	-	-
He and Sun 2019.08	58.23	54.5	62.17	-	-	-
He and Sun 2021.07	58.23	54.5	62.17	-	-	-
Char-based (LSTM) + bichar + softword 2019.08	56.75	50.55	60.11	-	-	-
Peng and Dredze [16] 2019.04	56.05	51.96	61.05	-	-	-
Peng and Dredze 2019.08	56.05	51.96	61.05	-	-	-
Peng and Dredze, 2015 2019.08	56.05	51.96	61.05	-	-	-
Peng and Dredze 2021.07	56.05	51.96	61.05	-	-	-
Char-based (LSTM) + bichar + ExSoftword 2019.08	56.02	58.93	53.38	-	-	-
Baseline + CNN (CNN + BiGRU + CRF) 2019.04	55.91	53.86	58.05	-	-	-
He and Sun [19] 2019.04	54.82	50.6	59.32	-	-	-
He and Sun 2019.08	54.82	50.6	59.32	-	-	-
He and Sun 2021.07	54.82	50.6	59.32	-	-	-
Baseline (BiGRU + CRF) 2019.04	53.8	49.02	58.8	-	-	-
Char-based (LSTM) 2019.08	52.77	46.11	55.29	-	-	-
Char-based (LSTM) + ExSoftword 2019.08	52.42	44.65	55.19	-	-	-
Peng and Dredze (2016)* 2018.05	0.5899	0.5528	0.6297	-	-	-
Lattice 2018.05	0.5879	0.5304	0.6225	-	-	-
He and Sun (2017b)* 2018.05	0.5823	0.545	0.6217	-	-	-
+bichar+softword 2018.05	0.5675	0.5055	0.6011	-	-	-
Peng and Dredze (2015) 2018.05	0.5605	0.5196	0.6105	-	-	-
He and Sun (2017a) 2018.05	0.5482	0.506	0.5932	-	-	-
Char baseline 2018.05	0.5277	0.4611	0.5529	-	-	-
+char+bichar LSTM 2018.05	0.5233	0.434	0.603	-	-	-
Word baseline 2018.05	0.4733	0.3602	0.5938	-	-	-
BERT 2021.06	-	-	-	67.12	66.88	67.33
RoBERTa 2021.06	-	-	-	68.49	67.81	68.15
ChineseBERT 2021.06	-	-	-	68.27	69.78	69.02
RoBERTa 2021.06	-	-	-	66.74	70.02	68.35
ChineseBERT 2021.06	-	-	-	68.75	72.97	70.8
Zhang and Yang (2018) 2021.12	-	-	-	53.04	62.25	58.79
Yan et al. (2019) 2021.12	-	-	-	-	-	58.17
Gui et al. (2019) 2021.12	-	-	-	57.14	66.67	59.92
Li et al. (2020b) 2021.12	-	-	-	-	-	68.55
Ma et al. (2020) 2021.12	-	-	-	70.94	67.02	70.5
W2NER 2021.12	-	-	-	70.84	73.87	72.32
CPLL 2023.05	-	-	-	-	-	68.23
Token-level Voting 2023.05	-	-	-	-	-	63.81
Entity-level Voting 2023.05	-	-	-	-	-	59.34
PRODEN-mlp 2023.05	-	-	-	-	-	61.85
LW loss 2023.05	-	-	-	-	-	64.26
Seqcrowd 2023.05	-	-	-	-	-	41.49
Clean data 2023.05	-	-	-	-	-	68.87