| Ensemble (Generative MBR) |
- Max F1 (WSJ)
- 71.9
- Mean F1 (WSJ)
- 70.4
|
Ensemble Distillation for Unsupervised Constituency Parsing
2023-10-03 |
코드 1 |
| Parse-Focused (NT=4500) |
- Max F1 (WSJ)
- 70.3
- Mean F1 (WSJ)
- 69.6
|
Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction
2024-07-23 |
코드 1 |
| Parse-Focused (NT=30) |
- Max F1 (WSJ)
- 68.4
- Mean F1 (WSJ)
- 67.4
|
Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction
2024-07-23 |
코드 1 |
| SemInfo-SCPCFG (1024NT) |
- Mean F1 (WSJ)
- 66.92
|
Improving Unsupervised Constituency Parsing via Maximizing Semantic Information
2024-10-03 |
코드 1 |
| Ensemble (Selective MBR) |
- Mean F1 (WSJ)
- 66.2
|
Ensemble Distillation for Unsupervised Constituency Parsing
2023-10-03 |
코드 1 |
| ReCAT |
- Mean F1 (WSJ)
- 65.0
|
Augmenting Transformers with Recursively Composed Multi-grained Representations
2023-09-28 |
코드 1 |
| DP in rank space |
- Mean F1 (WSJ)
- 64.1
|
Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs
2022-05-01 |
코드 1 · 코드 2 |
| inside-outside co-training + weak supervision |
- Max F1 (WSJ)
- 66.8
- Mean F1 (WSJ10)
- 74.2
- Mean F1 (WSJ)
- 63.1
|
Co-training an Unsupervised Constituency Parser with Weak Supervision
2021-10-05 |
코드 1 |
| Hashing (Parserker 2) |
- Max F1 (WSJ)
- 64.1
- Mean F1 (WSJ)
- 62.4
|
On Eliciting Syntax from Language Models via Hashing
2024-10-05 |
코드 1 |
| NBL-PCFG |
- Mean F1 (WSJ)
- 60.4
|
Neural Bi-Lexicalized PCFG Induction
2021-05-31 |
코드 1 |
| TN-PCFG (p=500) |
- Max F1 (WSJ)
- 61.4
- Mean F1 (WSJ)
- 57.7
|
PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols
2021-04-28 |
코드 1 |
| S-DIORA |
- Max F1 (WSJ)
- 63.96
- Max F1 (WSJ10)
- 71.8
- Mean F1 (WSJ)
- 57.6
|
Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders
논문 날짜 미기재 |
연결 없음 |
| Fast-R2D2 |
- Mean F1 (WSJ)
- 57.2
|
Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation
2022-03-01 |
코드 1 · 코드 2 |
| DIORA (+PP) |
- Max F1 (WSJ)
- 56.2
- Max F1 (WSJ10)
- 60.55
- Mean F1 (WSJ)
- 55.7
|
Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders
2019-06-01 |
코드 1 |
| Compound PCFG |
- Max F1 (WSJ)
- 60.1
- Max F1 (WSJ10)
- 68.8
- Mean F1 (WSJ)
- 55.2
|
Compound Probabilistic Context-Free Grammars for Grammar Induction
2019-06-24 |
코드 1 · 코드 2 |
| GPST(left to right parsing) |
- Mean F1 (WSJ)
- 55.2
|
Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale
2024-03-13 |
코드 1 · 코드 2 |
| Neural PCFG |
- Max F1 (WSJ)
- 52.6
- Mean F1 (WSJ)
- 50.8
|
Compound Probabilistic Context-Free Grammars for Grammar Induction
2019-06-24 |
코드 1 · 코드 2 |
| DIORA |
- Max F1 (WSJ)
- 49.6
- Mean F1 (WSJ10)
- 67.7
- Max F1 (WSJ10)
- 68.5
- Mean F1 (WSJ)
- 48.9
|
Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders
2019-06-01 |
코드 1 |
| ON-LSTM (tuned) |
- Max F1 (WSJ)
- 50.0
- Mean F1 (WSJ)
- 48.1
|
Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
2018-10-22 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 |
| DMV + invertible projector |
- Mean F1 (WSJ10)
- 60.2
- Mean F1 (WSJ)
- 47.9
|
Unsupervised Learning of Syntactic Structure with Invertible Neural Projections
2018-08-28 |
코드 1 |
| ON-LSTM |
- Max F1 (WSJ)
- 49.4
- Mean F1 (WSJ10)
- 65.1
- Max F1 (WSJ10)
- 66.8
- Mean F1 (WSJ)
- 47.7
|
Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
2018-10-22 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 |
| PRPN (tuned) |
- Max F1 (WSJ)
- 47.9
- Mean F1 (WSJ)
- 47.3
|
Neural Language Modeling by Jointly Learning Syntax and Lexicon
2017-11-02 |
코드 1 |
| URNNG |
- Max F1 (WSJ)
- 52.4
|
Unsupervised Recurrent Neural Network Grammars
2019-04-07 |
코드 1 |
| PRPN |
- Max F1 (WSJ)
- 38.1
|
Neural Language Modeling by Jointly Learning Syntax and Lexicon
2017-11-02 |
코드 1 |