Language Identification in the Limit

  title={Language Identification in the Limit},
  author={E. Mark Gold},
  journal={Inf. Control.},
  • E. M. Gold
  • Published 1 May 1967
  • Linguistics, Computer Science
  • Inf. Control.

Tables from this paper

Learning languages in a union

Learning Context Free Grammars in the Limit Aided by the Sample Distribution

  • Y. Seginer
  • Computer Science, Linguistics
    ECML Workshop on Learning Contex-Free Grammars
  • 2003
An algorithm for learning context free grammars from positive structural examples (unlabeled parse trees) is presented and it is shown that determining the parameter based on the sample distribution is often reasonable, given some weak assumptions on this distribution.

Grammatical Inference as Class Discrimination

A systematic approach is proposed that learns language boundaries based on subsequences from the sample sequences and is shown to show its effectiveness on a practical problem of music classification.

Language learning from stochastic input

This version yields, as a special case, Angluin's learner for the families of languages that are learnable from all texts (and not just from a set of texts of probability one).

Learnable Representations of Language A course at ESSLLI 2010

This work defines context free grammars where the non-terminals of the grammar correspond to the syntactic congruence classes, and a residuated lattice structure from the Galois connection between strings and contexts is defined, which allows a class of languages that includes some non-context free languages, many context-free languages and all regular languages.

A note on formal learning theory

Learning from equivalence queries and negative data

A concrete learning algorithm is presented which is able to identify a regular language in this setting and has polynomial complexity with respect to the size of the input set of negative data, the minimal DFA recognizing the target language, and the length of the given counterexamples.

Complexity in Language Acquisition

It is claimed that the real problem for language learning is the computational complexity of constructing a hypothesis from input data, and that target grammars need to be objective, in the sense that the primitive elements of these Grammars are based on objectively definable properties of the language itself.

Lecture notes on Knowledge-Based and Learning Systems by Maciej Lískiewicz Lecture 3 : Learning in the Limit II 1 The Pattern Languages

This work provides another example showing how the languages of arbitrary pattern languages may be applied to learn data structures.

Prudence in vacillatory language identification

This paper shows that prudence does not restrictTxtFex-identification, the criterion of success for identification of languages in a scenario in which an algorithmic deviceM is presented with all and only the elements of a languageL, andM conjectures a sequence of grammars.



Limiting recursion

  • E. Gold
  • Mathematics
    Journal of Symbolic Logic
  • 1965
A class of problems is called decidable if there is an algorithm which will give the answer to any problem of the class after a finite length of time. The purpose of this paper is to discuss the

Distributional Structure

This discussion will discuss how each language can be described in terms of a distributional structure, i.e. in Terms of the occurrence of parts relative to other parts, and how this description is complete without intrusion of other features such as history or meaning.

On the mechanization of syntactic analysis

There are three types of hierarchical relationships existing among the structural units of language: that of a class to its members, that of combination to its components, and that of an eme and its allos.

Developmental psycholinguistics

  • Part of the chapter
  • 1966

Usages of Natural Language." Informal report

  • 1966

A Course in Modern Linguistics." Macmillan, New York

  • 1958