Inside-Outside Reestimation From Partially Bracketed Corpora

The inside-outside algorithm for inferring the parameters of a stochastic context-free grammar is extended to take advantage of constituent information in a partially parsed corpus. Experiments on formal and natural language parsed corpora show that the new algorithm can achieve faster convergence and better modelling of hierarchical structure than the original one. In particular, over 90% of the constituents in the most likely analyses of a test set are compatible with test set constituents for a grammar trained on a corpus of 700 hand-parsed part-of-speech strings for ATIS sentences.

• Publication year

  1992

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  1992-02-23

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/981967.981984
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Stochastic Lexicalized Tree-adjoining Grammars

  1992cited by this paper
• Basic Methods of Probabilistic Context Free Grammars

  1992cited by this paper
• A Procedure for Quantitatively Comparing the Syntactic Coverage of English Grammars

  1991cited by this paper
• Probabilistic Parsing Method for Sentence Disambiguation

  1991cited by this paper
• The ATIS Spoken Language Systems Pilot Corpus

  1990cited by this paper
• Deducing Linguistic Structure from the Statistics of Large Corpora

  1990influential reference
• Parsing a Natural Language Using Mutual Information Statistics

  1990cited by this paper
• Applications of stochastic context-free grammars using the Inside-Outside algorithm

  1990cited by this paper
• Probabilistic Parsing Method for Sentence Disambiguation

  1989cited by this paper
• A tutorial on hidden Markov models and selected applications in speech recognition

  1989cited by this paper
• Trainable grammars for speech recognition

  1979influential reference
• Probabilistic Representation of Formal Languages

  1969cited by this paper

• Deep networks learn to parse uniform-depth context-free languages from local statistics

  2026cites this paper
• A Computational Simulation of Language Production in First Language Acquisition

  2025cites this paper
• Step-wise discriminative learning on uncertain annotations for word sense disambiguation

  2023cites this paper
• Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging

  2022cites this paper
• Learning Syntax from Naturally-Occurring Bracketings

  2021cites this paper
• Improved Latent Tree Induction with Distant Supervision via Span Constraints

  2021cites this paper
• Discriminative Learning for Probabilistic Context-Free Grammars based on Generalized H-Criterion

  2021cites this paper
• Reading assignment 2

  2021cites this paper
• Depth-Bounded Statistical PCFG Induction as a Model of Human Grammar Acquisition

  2021cites this paper
• Searching for universal model of amyloid signaling motifs using probabilistic context-free grammars

  2021cites this paper
• Learning synchronous context-free grammars with multiple specialised non-terminals for hierarchical phrase-based translation

  2020cites this paper
• Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders

  2020cites this paper
• Learning language (with) grammars: From teaching Latin to learning domain-specific grammars

  2020cites this paper
• Efficient Outside Computation

  2020cites this paper
• An Empirical Comparison of Unsupervised Constituency Parsing Methods

  2020cites this paper
• Efficient Second-Order TreeCRF for Neural Dependency Parsing

  2020cites this paper
• Learning Domain-specific Grammars from a Small Number of Examples

  2020cites this paper
• Consistent unsupervised estimators for anchored PCFGs

  2020cites this paper
• Neural Unsupervised Parsing Beyond English

  2019influential citation
• Compound Probabilistic Context-Free Grammars for Grammar Induction

  2019cites this paper
• Probabilistic grammars and hierarchical Dirichlet processes

  2018cites this paper
• Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples

  2018cites this paper
• Deep Latent Variable Models of Natural Language

  2018cites this paper
• A bidirectional mapping between English and CNF-based reasoners

  2018cites this paper
• Estimating probabilistic context-free grammars for proteins using contact map constraints

  2018cites this paper
• Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction

  2018cites this paper
• BTG-based Machine Translation with Simple Reordering Model using Structured Perceptron

  2017cites this paper
• Dependency Parsing with Partial Annotations: An Empirical Comparison

  2017cites this paper
• What Do Recurrent Neural Network Grammars Learn About Syntax?

  2016cites this paper
• Left-corner Methods for Syntactic Modeling with Universal Structural Constraints

  2016cites this paper
• Grammar Induction as Automated Transformation between Constraint Solving Models of Language

  2016cites this paper
• Language as skill: Intertwining comprehension and production

  2016cites this paper
• Active Learning for Dependency Parsing with Partial Annotation

  2016cites this paper
• Chapter 23 PARSING

  2016cites this paper
• Inside-Outside and Forward-Backward Algorithms Are Just Backprop (tutorial paper)

  2016cites this paper
• Spectral Methods for Natural Language Processing

  2016cites this paper
• Training Dependency Parsers with Partial Annotation

  2016cites this paper
• A statistical approach for the induction of a grammar of Arabic

  2015cites this paper
• Structured Language Models for Automatic Speech Transcription

  2015cites this paper
• Graphical Models with Structured Factors, Neural Factors, and Approximation-aware Training

  2015cites this paper
• Learning with Joint Inference and Latent Linguistic Structure in Graphical Models

  2015cites this paper
• Pointwise Prediction and Sequence-Based Reranking for Adaptable Part-of-Speech Tagging

  2015cites this paper
• Parse Imputation for Dependency Annotations

  2015cites this paper
• Semi-supervised slot tagging in spoken language understanding using recurrent transductive support vector machines

  2015cites this paper
• Inducing Grammars from Linguistic Universals and Realistic Amounts of Supervision

  2015cites this paper
• Pro and con: Internal speech and the evolution of complex language

  2015cites this paper
• Using WFSTs for Efficient EM Learning of Probabilistic CFGs and Their Extensions

  2014influential citation
• When Errors Become the Rule

  2014cites this paper
• Dynamic Programming for Energy Minimization

  2014cites this paper
• Low-Resource Semantic Role Labeling

  2014cites this paper
• Building Computational Resources: The URDU.KON-TB Treebank and the Urdu Parser

  2014cites this paper
• Unsupervised Learning for Syntactic Disambiguation

  2014cites this paper
• Efficient Latent-variable Grammars : Learning and Inference

  2014cites this paper
• A Dependency Parser for Tweets

  2014cites this paper
• Parsing low-resource languages using Gibbs sampling for PCFGs with latent annotations

  2014cites this paper
• Spectral Learning Techniques for Weighted Automata, Transducers, and Grammars

  2014cites this paper
• Unsupervised Spectral Learning of WCFG as Low-rank Matrix Completion

  2013cites this paper
• Accent Group modeling for improved prosody in statistical parameteric speech synthesis

  2013cites this paper
• Predictability effects in language acquisition

  2013cites this paper
• UCCA: A Semantics-based Grammatical Annotation Scheme

  2013cites this paper
• Discriminative Learning with Natural Annotations: Word Segmentation as a Case Study

  2013cites this paper
• Constraint Solving and Language Processing: 7th International Workshop, CSLP 2012, Orlans, France, September 13-14, 2012, Revised Selected Papers ... Computer Science and General Issues)

  2013influential citation
• Style-Specific Phrasing in Speech Synthesis

  2013cites this paper
• Intra-Lingual and Cross-Lingual Prosody Modelling

  2013cites this paper
• Breaking Out of Local Optima with Count Transforms and Model Recombination: A Study in Grammar Induction

  2013cites this paper
• Spectral Learning of Refinement HMMs

  2013cites this paper
• Probabilistic induction for an incremental semantic grammar

  2013cites this paper
• History Based Unsupervised Data Oriented Parsing

  2013cites this paper
• Language Acquisition as Statistical Inference

  2013cites this paper
• Incremental Grammar Induction from Child-Directed Dialogue Utterances

  2013cites this paper
• Grammar induction and parsing with dependency-and-boundary models

  2013influential citation
• The Role of Universal Constraints in Language Acquisition

  2012cites this paper
• Bootstrapping Dependency Grammar Inducers from Incomplete Sentence Fragments via Austere Models

  2012cites this paper
• On Language Acquisition through Womb Grammars

  2012cites this paper
• Spectral Learning of Latent-Variable PCFGs

  2012cites this paper
• Womb Grammars : Constraint Solving for Grammar Induction

  2012cites this paper
• The Geometry of Constrained Structured Prediction: Applications to Inference and Learning of Natural Language Syntax

  2012cites this paper
• Combinatory Categorial Grammars for Robust Natural Language Processing

  2012cites this paper
• Structured cognition and neural systems: from rats to language.

  2012cites this paper
• Rediscovering ACL Discoveries Through the Lens of ACL Anthology Network Citing Sentences

  2012cites this paper
• Soft Computing based Model for Identification of Pseudoknots in RNA Sequence using Learning Grammar

  2012cites this paper
• Learning alignment profiles for structural similarity measure

  2012cites this paper
• Three Dependency-and-Boundary Models for Grammar Induction

  2012cites this paper
• Decomposing and regenerating syntactic trees

  2012cites this paper
• Building a Hierarchical Annotated Corpus of Urdu: The URDU.KON-TB Treebank

  2012cites this paper
• Identifiability and Unmixing of Latent Parse Trees

  2012cites this paper
• Capitalization Cues Improve Dependency Grammar Induction

  2012cites this paper
• A Feature-Rich Constituent Context Model for Grammar Induction

  2012cites this paper
• Computational models of syntactic acquisition.

  2012cites this paper
• Inducing lexical entries for an incremental semantic grammar

  2012cites this paper
• MAP adaptation of stochastic grammars q

  2012cites this paper
• Probabilistic Grammar Induction in an Incremental Semantic Framework

  2012cites this paper
• Empirical Risk Minimization for Probabilistic Grammars: Sample Complexity and Hardness of Learning

  2012cites this paper
• Classification of research papers using citation links and citation types: Towards automatic review article generation.

  2011cites this paper
• Computational Models of Language Acquisition

  2011cites this paper
• Simple Unsupervised Grammar Induction from Raw Text with Cascaded Finite State Models

  2011cites this paper
• Using semantic cues to learn syntax Citation

  2011cites this paper
• Does it have to be trees?: data-driven dependency parsing with incomplete and noisy training data

  2011cites this paper
• Machine Learning for Natural Language Processing

  2011influential citation
• Parsing of Partially Bracketed Structures for Parse Selection

  2011cites this paper