Simple Robust Grammar Induction with Combinatory Categorial Grammars

We present a simple EM-based grammar induction algorithm for Combinatory Categorial Grammar (CCG) that achieves state-of-the-art performance by relying on a minimal number of very general linguistic principles. Unlike previous work on unsupervised parsing with CCGs, our approach has no prior language-specific knowledge, and discovers all categories automatically. Additionally, unlike other approaches, our grammar remains robust when parsing longer sentences, performing as well as or better than other systems. We believe this is a natural result of using an expressive grammar formalism with an extended domain of locality.

• Publication year

  2012

• Venue

  AAAI Conference on Artificial Intelligence

• Publication date

  2012-07-22

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.1609/aaai.v26i1.8355
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• On the Utility of Curricula in Unsupervised Learning of Probabilistic Grammars

  2011cited by this paper
• Grammar Induction from Text Using Small Syntactic Prototypes

  2011influential reference
• Inducing Tree-Substitution Grammars

  2010influential reference
• From Baby Steps to Leapfrog: How “Less is More” in Unsupervised Dependency Parsing

  2010influential reference
• Viterbi Training Improves Unsupervised Dependency Parsing

  2010influential reference
• Using Universal Linguistic Knowledge to Guide Grammar Induction

  2010influential reference
• From Statistics to Meaning

  2010cited by this paper
• Improving Unsupervised Dependency Parsing with Richer Contexts and Smoothing

  2009cited by this paper
• Extended Constituent-to-Dependency Conversion for English

  2007cited by this paper
• CCGbank: A Corpus of CCG Derivations and Dependency Structures Extracted from the Penn Treebank

  2007influential reference
• Better k-best Parsing

  2005cited by this paper
• Natural Language Parsing

  2005cited by this paper
• Natural language grammar induction with a generative constituent-context model

  2005cited by this paper
• Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency

  2004influential reference
• A Generative Constituent-Context Model for Improved Grammar Induction

  2002cited by this paper
• Generative Models for Statistical Parsing with Combinatory Categorial Grammar

  2002cited by this paper
• Book Reviews: The Syntactic Process

  2001influential reference
• Tree-Adjoining Grammars

  1997influential reference
• Statistical Learning by 8-Month-Old Infants

  1996cited by this paper
• Building a Large Annotated Corpus of English: The Penn Treebank

  1993influential reference
• Applications of stochastic context-free grammars using the Inside-Outside algorithm

  1990cited by this paper
• Polish Logic 1920-1939.

  1969cited by this paper
• Combinatory Logic, Volume I

  1959cited by this paper
• Éléments de syntaxe structurale

  1959cited by this paper
• A Quasi-Arithmetical Notation for Syntactic Description

  1953cited by this paper

• A Computational Simulation of Language Production in First Language Acquisition

  2025cites this paper
• Usage-based Grammar Induction from Minimal Cognitive Principles

  2024cites this paper
• Categorial Grammar Induction with Stochastic Category Selection

  2024cites this paper
• Categorial grammar induction from raw data

  2023cites this paper
• Development of a Multilingual CCG Treebank via Universal Dependencies Conversion

  2022cites this paper
• Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars

  2022cites this paper
• Constructing Multilingual CCG Treebanks from Universal Dependencies

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

  2021cites this paper
• Robust unsupervised discriminative dependency parsing

  2020cites this paper
• Montague Grammar Induction

  2020cites this paper
• A Survey of Unsupervised Dependency Parsing

  2020cites this paper
• The Return of Lexical Dependencies: Neural Lexicalized PCFGs

  2020cites this paper
• Supertagging with CCG primitives

  2020cites this paper
• Extracting CCGs for Plan Recognition in RTS Games

  2019cites this paper
• A Probabilistic Approach to Unsupervised Induction of Combinatory Categorial Grammar in Situated Human-Robot Interaction

  2018cites this paper
• Learning Combinatory Categorial Grammars for Plan Recognition

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

  2018cites this paper
• Towards Understanding Object-Directed Actions: A Generative Model for Grounding Syntactic Categories of Speech Through Visual Perception

  2018cites this paper
• Combining Generative and Discriminative Approaches to Unsupervised Dependency Parsing via Dual Decomposition

  2017cites this paper
• Grammar Induction for Minimalist Grammars using Variational Bayesian Inference : A Technical Report

  2017cites this paper
• Grammar induction for mildly context sensitive languages using variational Bayesian inference

  2017cites this paper
• Mapping to Declarative Knowledge for Word Problem Solving

  2017cites this paper
• Mildly context sensitive grammar induction and variational bayesian inference

  2017cites this paper
• Left-corner Methods for Syntactic Modeling with Universal Structural Constraints

  2016cites this paper
• Linguistically Motivated Combinatory Categorial Grammar Induction

  2016cites this paper
• A Supertag-Context Model for Weakly-Supervised CCG Parser Learning

  2015cites this paper
• Unsupervised Dependency Parsing: Let’s Use Supervised Parsers

  2015cites this paper
• Unsupervised grammar induction with Combinatory Categorial Grammars

  2015cites this paper
• Probing the Linguistic Strengths and Limitations of Unsupervised Grammar Induction

  2015influential citation
• Inducing Grammars from Linguistic Universals and Realistic Amounts of Supervision

  2015cites this paper
• Labeled Grammar Induction with Minimal Supervision

  2015cites this paper
• A Linguistics-Driven Approach to Statistical Parsing for Low-Resourced Languages

  2015influential citation
• Using lexical, syntactic and semantic features for non-terminal grammar rule induction in Spoken Dialogue Systems

  2014cites this paper
• Scalable semi-supervised grammar induction using cross-linguistically parameterized syntactic prototypes

  2014cites this paper
• SemEval-2014 Task 2: Grammar Induction for Spoken Dialogue Systems

  2014cites this paper
• Breaking Out of Local Optima with Count Transforms and Model Recombination: A Study in Grammar Induction

  2013influential citation
• Grammar induction and parsing with dependency-and-boundary models

  2013influential citation
• An HDP Model for Inducing Combinatory Categorial Grammars

  2013influential citation
• Induction of Linguistic Structure with Combinatory Categorial Grammars

  2012cites this paper
• Improved Combinatory Categorial Grammar Induction with Boundary Words and Bayesian Inference

  2012influential citation