A computational study of cross-situational techniques for learning word-to-meaning mappings

  title={A computational study of cross-situational techniques for learning word-to-meaning mappings},
  author={Jeffrey Mark Siskind},
  • J. Siskind
  • Published 1 October 1996
  • Computer Science
  • Cognition

Figures and Tables from this paper

A computational model of adults' performance in naming objects using cross-situational learning

This work investigates the performance of a simplified variant of the general-purpose Neural Modeling Fields (NMF) categorization mechanism to infer the correct word-referent mapping in a cross-situational learning scenario that simulates experiments with adult subjects.

A Computational Model for the Item-Based Induction of Construction Networks

This article explores how the gradual emergence of a network consisting of constructions at varying degrees of complexity can be modeled computationally and shows how cross-situational learning can be applied consistently to learn correspondences between form and meaning beyond such simple correspondences.

Mechanisms for cross-situational learning of word-referent mappings: Empirical and modeling evidence

Language acquisition is a ubiquitous, challenging problem involving fundamental cognitive abilities of attention, learning, and memory. From infants to adult travelers, language learners are faced

A cross-situational algorithm for learning a lexicon using Neural modeling fields

This work investigates the possibility of applying the deterministic Neural Modeling Fields (NMF) categorization mechanism to infer the correct object-word mapping and shows that use of two levels of hierarchy of NMF allows the inference of the correctobject-word mapped.

Cross-situational learning of large lexicons with finite memory

The main finding is that it is possible for this learner to acquire a human-scale lexicon by adulthood with word-exposure and memory-decay rates that are consistent with empirical research on childhood word learning, as long as the degree of referential uncertainty is not too high or the learner employs a mutual exclusivity constraint.

Integrating Syntactic Knowledge into a Model of Cross-situational Word Learning

A probabilistic model of word learn- ing which integrates cross-situational evidence and the knowledge of lexical categories into a single learning mechanism is presented.

A usage-based model for the acquisition of syntactic constructions and its application in spoken language understanding

The model’s generalization abilities are initially limited, increase over time, and finally converge, suggesting that the employed mechanisms allow accurate learning without (severe) deterioration of knowledge already captured by the network during further processing of examples.

A joint model of word segmentation and meaning acquisition through cross-situational learning.

It is argued that XSL is not just a mechanism for word-to-meaning mapping, but that it provides strong cues for proto-lexical word segmentation, and results from simulations show that the model is not only capable of replicating behavioral data on word learning in artificial languages, but also shows effective learning of word segments and their meanings from continuous speech.

Learning Word-to-Meaning Mappings

Computer simulation demonstrates that algorithms for solving the mapping problem are developed, based on the intuitive notions of cross-situational learning and the principle of contrast, which motivates the hypothesis that children use such techniques, inter alia, when learning language.



Lexical Acquisition as Constraint Satisfaction

A novel strategy is presented that is capable of learning the word-to-meaning mappings for as many as 10,000 words given corpora of 20,000 utterances and is accomplished in a language independent fashion without any reference to the syntax of the language being learned.

Acquiring Core Meanings of Words, Represented as Jackendoff-Style Conceptual Structures, from Correlated Streams of Linguistic and Non-Linguistic Input

The theory underlying the system, the representations and algorithms used in the implementation, the semantic constraints which support the heuristics necessary to achieve tractable learning, the limitations of the current theory and the implications of this work for language acquisition research are discussed.

The acquisition of lexical semantics for spatial terms: a connectionist model of perceptual categorization

This thesis describes a connectionist model which learns to perceive spatial events and relations in simple movies of 2-dimensional objects, so as to name the events and relations as a speaker of a

Naive physics, event perception, lexical semantics, and language acquisition

Algorithms are presented which utilize a cross-situational learning strategy whereby the learner finds a language model which is consistent across several utterances paired with their non-linguistic context, and three claims about event perception and the process of grounding language in visual perception are advanced.

Using sound to solve syntactic problems: the role of phonology in grammatical category assignments.

  • M. H. Kelly
  • Linguistics, Psychology
    Psychological review
  • 1992
One ubiquitous problem in language processing involves the assignment of words to the correct grammatical category, such as noun or verb. In general, semantic and syntactic cues have been cited as

Do infants perceive word boundaries? An empirical study of the bootstrapping of lexical acquisition.

Three-day-old infants were tested with a non-nutritive sucking paradigm, and the results of two experiments suggest that infants can discriminate between items that contain a word boundary and items that do not, lending plausibility to the hypothesis that infants might use word boundary cues during lexical acquisition.

Learning Word Meanings From Examples

A computer program that uses syntactic constraints to derive the meanings of verbs from an analysis of simple English example stories is described, an extension of Winston's (Winston 1975) program that learned the structural descriptions of blocks world scenes.

Acquiring Lexical Knowledge from Text: A Case Study

This paper describes an approach to constructing new lexical entries in a gradual process by analyzing a sequence of example texts to permit the graceful tolerance of new words while enabling the automated extension of the lexicon.