natural-language-processing-8

Constituency Grammar Induction

3260 papers • 126 benchmarks • 313 datasets

Inducing a constituency-based phrase structure grammar.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in constituency-grammar-induction-8

Trend

Dataset

Best Model

Actions

PTB Diagnostic ECG Database

Libraries

i

Use these libraries to find constituency-grammar-induction-8 models and implementations

Datasets

Penn Treebank

PTB Diagnostic ECG Database

Subtasks

No subtasks available.

Most implemented papers

Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks

Aaron C. Courville, Alessandro Sordoni, Shawn Tan, Yikang Shen•Wed Sep 26 2018

The novel recurrent architecture, ordered neurons LSTM (ON-LSTM), achieves good performance on four different tasks: language modeling, unsupervised parsing, targeted syntactic evaluation, and logical inference.

345

Content

0

Paper Graph

Compound Probabilistic Context-Free Grammars for Grammar Induction

Chris Dyer, Alexander M. Rush, Yoon Kim•Sun Jun 23 2019

A formalization of the grammar induction problem that models sentences as being generated by a compound probabilistic context free grammar, which is modulated by a per-sentence continuous latent variable, which induces marginal dependencies beyond the traditional context-free assumptions.

162 0

Paper Graph

Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs

Kewei Tu, Songlin Yang, Wei Liu•Sat Apr 30 2022

This work uses tensor rank decomposition (aka. CPD) to decrease inference computational complexities for a subset of FGGs subsuming HMMs and PCFGs, and conducts experiments on HMM language modeling and unsupervised PCFG parsing, showing better performance.

10 0

Paper Graph

Neural Language Modeling by Jointly Learning Syntax and Lexicon

Aaron C. Courville, Zhouhan Lin, Yikang Shen, Chin-Wei Huang•Tue Oct 31 2017

A novel neural language model, called the Parsing-Reading-Predict Networks (PRPN), that can simultaneously induce the syntactic structure from unannotated sentences and leverage the inferred structure to learn a better language model is proposed.

182 0

Paper Graph

Unsupervised Recurrent Neural Network Grammars

Chris Dyer, Lei Yu, Gábor Melis, Alexander M. Rush, A. Kuncoro, Yoon Kim•Sat Apr 06 2019

An inference network parameterized as a neural CRF constituency parser is developed to maximize the evidence lower bound and apply amortized variational inference to unsupervised learning of RNNGs.

120 0

Paper Graph

Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders

A. McCallum, Mohit Iyyer, Pat Verga, Andrew Drozdov, Mohit Yadav•Tue Apr 02 2019

DIORA is introduced, a fully-unsupervised method for discovering syntax that simultaneously learns representations for constituents within the induced tree that outperforms previously reported results for unsupervised binary constituency parsing on the benchmark WSJ dataset.

128 0

Paper Graph

Unsupervised Learning of Syntactic Structure with Invertible Neural Projections

Graham Neubig, Junxian He, Taylor Berg-Kirkpatrick•Tue Jul 31 2018

A novel generative model is proposed that jointly learns discrete syntactic structure and continuous word representations in an unsupervised fashion by cascading an invertible neural network with a structured generative prior so long as the prior is well-behaved.

41 0

Paper Graph

Visually Grounded Compound PCFGs

Ivan Titov, Yanpeng Zhao•Thu Sep 24 2020

This work studies visually grounded grammar induction and learns a constituency parser from both unlabeled text and its visual groundings, and shows that using an extension of probabilistic context-free grammar model, it can do fully-differentiable end-to-end visually grounded learning.

46 0

Paper Graph

PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols

Kewei Tu, Songlin Yang, Yanpeng Zhao•Tue Apr 27 2021

A new parameterization form of PCFGs based on tensor decomposition is presented, which has at most quadratic computational complexity in the symbol number and therefore allows us to use a much larger number of symbols.

28 0

Paper Graph

Neural Bi-Lexicalized PCFG Induction

Kewei Tu, Songlin Yang, Yanpeng Zhao•Sun May 30 2021

This paper proposes an approach to parameterize L-PCFGs without making implausible independence assumptions, which directly models bilexical dependencies and meanwhile reduces both learning and representation complexities of L- PCFGs.

24 0

Paper Graph

Adding a benchmark result helps the community track progress.