Constituency Parsing on PTB Diagnostic ECG Database

Metric: Mean F1 (WSJ) (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Mean F1 (WSJ)▼	Extra Data	Paper	Date↕	Code
1	Ensemble (Generative MBR)	70.4	No	Ensemble Distillation for Unsupervised Constitue...	2023-10-03	Code
2	Parse-Focused (NT=4500)	69.6	No	Structural Optimization Ambiguity and Simplicity...	2024-07-23	Code
3	Parse-Focused (NT=30)	67.4	No	Structural Optimization Ambiguity and Simplicity...	2024-07-23	Code
4	SemInfo-SCPCFG (1024NT)	66.92	No	Improving Unsupervised Constituency Parsing via ...	2024-10-03	Code
5	Ensemble (Selective MBR)	66.2	No	Ensemble Distillation for Unsupervised Constitue...	2023-10-03	Code
6	ReCAT	65	No	Augmenting Transformers with Recursively Compose...	2023-09-28	Code
7	DP in rank space	64.1	No	Dynamic Programming in Rank Space: Scaling Struc...	2022-05-01	Code
8	inside-outside co-training + weak supervision	63.1	Yes	Co-training an Unsupervised Constituency Parser ...	2021-10-05	Code
9	Hashing (Parserker 2)	62.4	No	On Eliciting Syntax from Language Models via Has...	2024-10-05	Code
10	NBL-PCFG	60.4	No	Neural Bi-Lexicalized PCFG Induction	2021-05-31	Code
11	TN-PCFG (p=500)	57.7	No	PCFGs Can Do Better: Inducing Probabilistic Cont...	2021-04-28	Code
12	S-DIORA	57.6	No	-	-	-
13	Fast-R2D2	57.2	No	Fast-R2D2: A Pretrained Recursive Neural Network...	2022-03-01	Code
14	DIORA (+PP)	55.7	No	-	-	Code
15	Compound PCFG	55.2	No	Compound Probabilistic Context-Free Grammars for...	2019-06-24	Code
16	GPST(left to right parsing)	55.2	No	Generative Pretrained Structured Transformers: U...	2024-03-13	Code
17	Neural PCFG	50.8	No	Compound Probabilistic Context-Free Grammars for...	2019-06-24	Code
18	DIORA	48.9	No	-	-	Code
19	ON-LSTM (tuned)	48.1	No	Ordered Neurons: Integrating Tree Structures int...	2018-10-22	Code
20	DMV + invertible projector	47.9	No	Unsupervised Learning of Syntactic Structure wit...	2018-08-28	Code
21	ON-LSTM	47.7	No	Ordered Neurons: Integrating Tree Structures int...	2018-10-22	Code
22	PRPN (tuned)	47.3	No	Neural Language Modeling by Jointly Learning Syn...	2017-11-02	Code

#1Ensemble (Generative MBR)SOTA
70.4
Mean F1 (WSJ)· 2023-10-03
Ensemble Distillation for Unsupervised Constituency Parsing Code
#2Parse-Focused (NT=4500)
69.6
Mean F1 (WSJ)· 2024-07-23
Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction Code
#3Parse-Focused (NT=30)
67.4
Mean F1 (WSJ)· 2024-07-23
Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction Code
#4SemInfo-SCPCFG (1024NT)
66.92
Mean F1 (WSJ)· 2024-10-03
Improving Unsupervised Constituency Parsing via Maximizing Semantic Information Code
#5Ensemble (Selective MBR)
66.2
Mean F1 (WSJ)· 2023-10-03
Ensemble Distillation for Unsupervised Constituency Parsing Code
#6ReCATSOTA
65
Mean F1 (WSJ)· 2023-09-28
Augmenting Transformers with Recursively Composed Multi-grained Representations Code
#7DP in rank spaceSOTA
64.1
Mean F1 (WSJ)· 2022-05-01
Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs Code
#8inside-outside co-training + weak supervisionSOTA
63.1
Mean F1 (WSJ)· Extra Data· 2021-10-05
Co-training an Unsupervised Constituency Parser with Weak Supervision Code
#9Hashing (Parserker 2)
62.4
Mean F1 (WSJ)· 2024-10-05
On Eliciting Syntax from Language Models via Hashing Code
#10NBL-PCFGSOTA
60.4
Mean F1 (WSJ)· 2021-05-31
Neural Bi-Lexicalized PCFG Induction Code
#11TN-PCFG (p=500)SOTA
57.7
Mean F1 (WSJ)· 2021-04-28
PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols Code
#12S-DIORA
57.6
Mean F1 (WSJ)
No paper
#13Fast-R2D2
57.2
Mean F1 (WSJ)· 2022-03-01
Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation Code
#14DIORA (+PP)
55.7
Mean F1 (WSJ)
No paperCode
#15Compound PCFGSOTA
55.2
Mean F1 (WSJ)· 2019-06-24
Compound Probabilistic Context-Free Grammars for Grammar Induction Code
#16GPST(left to right parsing)
55.2
Mean F1 (WSJ)· 2024-03-13
Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale Code
#17Neural PCFG
50.8
Mean F1 (WSJ)· 2019-06-24
Compound Probabilistic Context-Free Grammars for Grammar Induction Code
#18DIORA
48.9
Mean F1 (WSJ)
No paperCode
#19ON-LSTM (tuned)SOTA
48.1
Mean F1 (WSJ)· 2018-10-22
Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks Code
#20DMV + invertible projectorSOTA
47.9
Mean F1 (WSJ)· 2018-08-28
Unsupervised Learning of Syntactic Structure with Invertible Neural Projections Code
#21ON-LSTM
47.7
Mean F1 (WSJ)· 2018-10-22
Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks Code
#22PRPN (tuned)SOTA
47.3
Mean F1 (WSJ)· 2017-11-02
Neural Language Modeling by Jointly Learning Syntax and Lexicon Code