Constituency Parsing on Penn Treebank

Metric: F1 score (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	F1 score▼	Extra Data	Paper	Date↕	Code
1	Hashing + XLNet	96.43	No	To be Continuous, or to be Discrete, Those are B...	2024-06-12	Code
2	SAPar + XLNet	96.4	No	Improving Constituency Parsing with Span Attention	2020-10-15	Code
3	Label Attention Layer + HPSG + XLNet	96.38	No	Rethinking Self-Attention: Towards Interpretabil...	2019-11-10	Code
4	Attach-Juxtapose Parser + XLNet	96.34	No	Strongly Incremental Constituency Parsing with G...	2020-10-27	Code
5	Head-Driven Phrase Structure Grammar Parsing (Joint) + XLNet	96.33	No	Head-Driven Phrase Structure Grammar Parsing on ...	2019-07-05	Code
6	CRF Parser + RoBERTa	96.32	No	Fast and Accurate Neural CRF Constituency Parsing	2020-08-09	Code
7	Hashing + Bert	96.03	No	To be Continuous, or to be Discrete, Those are B...	2024-06-12	Code
8	N-ary semi-markov + BERT-large	95.92	No	-	-	Code
9	NFC + BERT-large	95.92	No	Investigating Non-local Features for Neural Cons...	2021-09-27	Code
10	Head-Driven Phrase Structure Grammar Parsing (Joint) + BERT	95.84	No	Head-Driven Phrase Structure Grammar Parsing on ...	2019-07-05	Code
11	CRF Parser + BERT	95.69	No	Fast and Accurate Neural CRF Constituency Parsing	2020-08-09	Code
12	CNN Large + fine-tune	95.6	No	Cloze-driven Pretraining of Self-attention Netwo...	2019-03-19	-
13	SpanRel	95.5	No	Generalizing Natural Language Analysis through S...	2019-11-10	Code
14	Tetra Tagging	95.44	No	Tetra-Tagging: Word-Synchronous Parsing with Lin...	2019-04-22	Code
15	Self-attentive encoder + ELMo	95.13	No	Constituency Parsing with a Self-Attentive Encoder	2018-05-02	Code
16	Model combination	94.66	No	Improving Neural Parsing by Disentangling Model ...	2017-07-10	-
17	LSTM Encoder-Decoder + LSTM-LM	94.47	No	Direct Output Connection for a High-Rank Languag...	2018-08-30	Code
18	LSTM Encoder-Decoder + LSTM-LM	94.32	No	-	-	Code
19	In-order	94.2	No	In-Order Transition-based Constituent Parsing	2017-07-17	Code
20	CRF Parser	94.12	No	Fast and Accurate Neural CRF Constituency Parsing	2020-08-09	Code
21	Semi-supervised LSTM-LM	93.8	No	-	-	Code
22	Stack-only RNNG	93.6	No	What Do Recurrent Neural Network Grammars Learn ...	2016-11-17	Code
23	Transformer	92.7	No	Attention Is All You Need	2017-06-12	Code
24	Parse fusion	92.6	Yes	-	-	Code
25	Semi-supervised LSTM	92.1	No	Grammar as a Foreign Language	2014-12-23	Code
26	Self-training	92.1	Yes	-	-	Code

#1Hashing + XLNetSOTA
96.43
F1 score· 2024-06-12
To be Continuous, or to be Discrete, Those are Bits of Questions Code
#2SAPar + XLNetSOTA
96.4
F1 score· 2020-10-15
Improving Constituency Parsing with Span Attention Code
#3Label Attention Layer + HPSG + XLNetSOTA
96.38
F1 score· 2019-11-10
Rethinking Self-Attention: Towards Interpretability in Neural Parsing Code
#4Attach-Juxtapose Parser + XLNet
96.34
F1 score· 2020-10-27
Strongly Incremental Constituency Parsing with Graph Neural Networks Code
#5Head-Driven Phrase Structure Grammar Parsing (Joint) + XLNetSOTA
96.33
F1 score· 2019-07-05
Head-Driven Phrase Structure Grammar Parsing on Penn Treebank Code
#6CRF Parser + RoBERTa
96.32
F1 score· 2020-08-09
Fast and Accurate Neural CRF Constituency Parsing Code
#7Hashing + Bert
96.03
F1 score· 2024-06-12
To be Continuous, or to be Discrete, Those are Bits of Questions Code
#8N-ary semi-markov + BERT-large
95.92
F1 score
No paperCode
#9NFC + BERT-large
95.92
F1 score· 2021-09-27
Investigating Non-local Features for Neural Constituency Parsing Code
#10Head-Driven Phrase Structure Grammar Parsing (Joint) + BERT
95.84
F1 score· 2019-07-05
Head-Driven Phrase Structure Grammar Parsing on Penn Treebank Code
#11CRF Parser + BERT
95.69
F1 score· 2020-08-09
Fast and Accurate Neural CRF Constituency Parsing Code
#12CNN Large + fine-tuneSOTA
95.6
F1 score· 2019-03-19
Cloze-driven Pretraining of Self-attention Networks
#13SpanRel
95.5
F1 score· 2019-11-10
Generalizing Natural Language Analysis through Span-relation Representations Code
#14Tetra Tagging
95.44
F1 score· 2019-04-22
Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference Code
#15Self-attentive encoder + ELMoSOTA
95.13
F1 score· 2018-05-02
Constituency Parsing with a Self-Attentive Encoder Code
#16Model combinationSOTA
94.66
F1 score· 2017-07-10
Improving Neural Parsing by Disentangling Model Combination and Reranking Effects
#17LSTM Encoder-Decoder + LSTM-LM
94.47
F1 score· 2018-08-30
Direct Output Connection for a High-Rank Language Model Code
#18LSTM Encoder-Decoder + LSTM-LM
94.32
F1 score
No paperCode
#19In-order
94.2
F1 score· 2017-07-17
In-Order Transition-based Constituent Parsing Code
#20CRF Parser
94.12
F1 score· 2020-08-09
Fast and Accurate Neural CRF Constituency Parsing Code
#21Semi-supervised LSTM-LM
93.8
F1 score
No paperCode
#22Stack-only RNNGSOTA
93.6
F1 score· 2016-11-17
What Do Recurrent Neural Network Grammars Learn About Syntax?Code
#23Transformer
92.7
F1 score· 2017-06-12
Attention Is All You Need Code
#24Parse fusion
92.6
F1 score· Extra Data
No paperCode
#25Semi-supervised LSTMSOTA
92.1
F1 score· 2014-12-23
Grammar as a Foreign Language Code
#26Self-training
92.1
F1 score· Extra Data
No paperCode