HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Constituency Grammar Induction On Ptb

评估指标

Max F1 (WSJ)

评测结果

各个模型在此基准测试上的表现结果

模型名称
Max F1 (WSJ)
Paper TitleRepository
PRPN38.1Neural Language Modeling by Jointly Learning Syntax and Lexicon
Ensemble (Selective MBR)-Ensemble Distillation for Unsupervised Constituency Parsing-
ReCAT-Augmenting Transformers with Recursively Composed Multi-grained Representations-
ON-LSTM49.4Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
DIORA (+PP)56.2Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders
Parse-Focused (NT=30)68.4Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction-
Ensemble (Generative MBR)71.9Ensemble Distillation for Unsupervised Constituency Parsing-
inside-outside co-training + weak supervision66.8Co-training an Unsupervised Constituency Parser with Weak Supervision
Compound PCFG60.1Compound Probabilistic Context-Free Grammars for Grammar Induction
TN-PCFG (p=500)61.4PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols
ON-LSTM (tuned)50.0Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
DIORA49.6Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders
URNNG52.4Unsupervised Recurrent Neural Network Grammars
GPST(left to right parsing)-Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale
Neural PCFG52.6Compound Probabilistic Context-Free Grammars for Grammar Induction
Parse-Focused (NT=4500)70.3Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction-
S-DIORA63.96Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders-
DP in rank space-Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs
Hashing (Parserker 2)64.1On Eliciting Syntax from Language Models via Hashing
PRPN (tuned)47.9Neural Language Modeling by Jointly Learning Syntax and Lexicon
0 of 23 row(s) selected.