Minimally Supervised Model of Early Language Acquisition

Theories of human language acquisition assume that learning to understand sentences is a partially-supervised task (at best). Instead of using 'gold-standard' feedback, we train a simplified "Baby" Semantic Role Labeling system by combining world knowledge and simple grammatical constraints to form a potentially noisy training signal. This combination of knowledge sources is vital for learning; a training signal derived from a single component leads the learner astray. When this largely unsupervised training approach is applied to a corpus of child directed speech, the BabySRL learns shallow structural cues that allow it to mimic striking behaviors found in experiments with children and begin to correctly identify agents in a sentence.

• Publication year

  2009

• Venue

  Conference on Computational Natural Language Learning

• Publication date

  2009-06-04

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1596374.1596391
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Young Infants' Expectations About Self-propelled Objects

  2009cited by this paper
• First Language

  2009cited by this paper
• Baby SRL: Modeling Early Language Acquisition.

  2008influential reference
• A computational usage-based model for learning general properties of semantic roles

  2007cited by this paper
• The Necessity of Syntactic Parsing for Semantic Role Labeling

  2005cited by this paper
• Learning and Inference over Constrained Output

  2005cited by this paper
• The Proposition Bank: An Annotated Corpus of Semantic Roles

  2005cited by this paper
• Predicted Errors in Early Verb Learning

  2005cited by this paper
• Introduction to the CoNLL-2004 Shared Task: Semantic Role Labeling

  2004cited by this paper
• From TreeBank to PropBank

  2002cited by this paper
• Seeing pink elephants: fourteen-month-olds' interpretations of novel nouns and adjectives.

  2001cited 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
• Markedness and Subject Choice in Optimality Theory

  1999cited by this paper
• Thematic Roles and the Individuation of Events

  1998cited by this paper
• Linear Concepts and Hidden Variables

  1997cited by this paper
• Statistical Parsing with a Context-Free Grammar and Word Statistics

  1997cited by this paper
• Structural limits on verb mapping: the role of analogy in children's interpretations of sentences.

  1996cited by this paper
• The CHILDES project: tools for analyzing talk

  1992cited by this paper
• Learnability and Cognition

  1991cited by this paper
• Thematic proto-roles and argument selection

  1991cited by this paper
• Children use syntax to learn verb meanings

  1990cited by this paper
• The Mental Representation of Grammatical Relations

  1986cited by this paper
• The Mental representation of grammatical relations

  1985cited by this paper
• Comprehension strategies in two and three year olds: animate agents or probable events?

  1977cited by this paper
• PSYCHOLOGICAL SCIENCE Research Article Learning Words and Rules Abstract Knowledge of Word Order in Early Sentence Comprehension

  year unknowncited by this paper

• A Knowledge-Based Language Model: Deducing Grammatical Knowledge in a Multi-Agent Language Acquisition Simulation

  2025cites this paper
• Unsupervised Acquisition of Discrete Grammatical Categories

  2025cites this paper
• MULTIMEDIA CURRICULUM LEARNING FOR LANGUAGE ACQUISITION

  2023cites this paper
• A dynamic network analysis of emergent grammar

  2019cites this paper
• Bootstrapping into Filler-Gap: An Acquisition Story

  2014cites this paper
• Starting from Scratch in Semantic Role Labeling: Early Indirect Supervision

  2013cites this paper
• Macho: Writing Programs with Natural Language and Examples

  2012cites this paper
• Rol semantikoen etiketatze automatikoa: rol multzoak eta hautapen murriztapenak

  2011cites this paper
• Minimal supervision for language learning: bootstrapping global patterns from local knowledge

  2011cites this paper
• Detecting and Combining Programming Patterns

  2010cites this paper
• Starting from Scratch in Semantic Role Labeling

  2010influential citation
• Semantic Role Labeling: Past, Present and Future

  2009cites this paper