Categorial Grammar Induction with Stochastic Category Selection

Grammar induction, the task of learning a set of syntactic rules from minimally annotated training data, provides a means of exploring the longstanding question of whether humans rely on innate knowledge to acquire language. Of the various formalisms available for grammar induction, categorial grammars provide an appealing option due to their transparent interface between syntax and semantics. However, to obtain competitive results, previous categorial grammar inducers have relied on shortcuts such as part-of-speech annotations or an ad hoc bias term in the objective function to ensure desirable branching behavior. We present a categorial grammar inducer that eliminates both shortcuts: it learns from raw data, and does not rely on a biased objective function. This improvement is achieved through a novel stochastic process used to select the set of available syntactic categories. On a corpus of English child-directed speech, the model attains a recall-homogeneity of 0.48, a large improvement over previous categorial grammar inducers.

• Publication year

  2024

• Venue

  International Conference on Language Resources and Evaluation

• Publication date

  2024-05-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.63317/3y3r87q75ad4
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Learning a Grammar Inducer from Massive Uncurated Instructional Videos

  2022cited by this paper
• Depth-Bounded Statistical PCFG Induction as a Model of Human Grammar Acquisition

  2021cited by this paper
• Video-aided Unsupervised Grammar Induction

  2021cited by this paper
• On Aspects of the Theory of Syntax

  2021cited by this paper
• Character-based PCFG Induction for Modeling the Syntactic Acquisition of Morphologically Rich Languages

  2021influential reference
• Supertagging the Long Tail with Tree-Structured Decoding of Complex Categories

  2020cited by this paper
• Syntactic Structure from Deep Learning

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

  2020cited by this paper
• Visually Grounded Compound PCFGs

  2020cited by this paper
• Compound Probabilistic Context-Free Grammars for Grammar Induction

  2019cited by this paper
• Attention is All you Need

  2017cited by this paper
• Labeled Grammar Induction with Minimal Supervision

  2015cited by this paper
• Syntactic Islands and Learning Biases: Combining Experimental Syntax and Computational Modeling to Investigate the Language Acquisition Problem

  2013cited by this paper
• An HDP Model for Inducing Combinatory Categorial Grammars

  2013cited by this paper
• Simple Robust Grammar Induction with Combinatory Categorial Grammars

  2012cited by this paper
• Accurate Unbounded Dependency Recovery using Generalized Categorial Grammars

  2012cited by this paper
• First Language

  2009cited by this paper
• CCGbank: A Corpus of CCG Derivations and Dependency Structures Extracted from the Penn Treebank

  2007cited by this paper
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

  2005cited by this paper
• The estimation of stochastic context-free grammars using the Inside-Outside algorithm

  2003cited by this paper
• The Infinite Hidden Markov Model

  2002cited by this paper
• A Generative Constituent-Context Model for Improved Grammar Induction

  2002cited by this paper
• The CHILDES Project: Tools for Analyzing Talk (third edition): Volume I: Transcription format and programs, Volume II: The database

  2000cited by this paper
• Two Experiments on Learning Probabilistic Dependency Grammars from Corpora

  1992cited by this paper
• Syntactic Processing

  1979cited by this paper
• Language Identification in the Limit

  1967cited by this paper
• A Quasi-Arithmetical Notation for Syntactic Description

  1953cited by this paper

• No citing papers are available for this paper.