Synthesizing enumeration techniques for language learning

Ganesh R. Baliga; John Case; Sanjay Jain

doi:10.1145/238061.238090

Synthesizing enumeration techniques for language learning

Ganesh R. Baliga
, John Case
, Sanjay Jain

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

14 Scopus citations

Abstract

This paper provides positive and negative results on algorithmically synthesizing, from grammars and from decision procedures for classes and languages, learning machines for identifying, from positive data, grammars for the languages in those classes. In the process, the uniformly decidable classes of recursive languages that can be behaviorally correctly identified from positive data are surprisingly characterized by Angluin's 1980 Condition 2 (the subset for principle for preventing over generalization).

Original language	English (US)
Title of host publication	Proceedings of the ninth annual conference on Computational learning theory, COLT 1996
Pages	169-180
Number of pages	12
ISBN (Electronic)	9780897918114
DOIs	https://doi.org/10.1145/238061.238090
State	Published - Jan 1 1996
Event	9th Annual Conference on Computational Learning Theory, COLT 1996 - Desenzano del Garda, Italy Duration: Jun 28 1996 → Jul 1 1996

Publication series

Name	Proceedings of the Annual ACM Conference on Computational Learning Theory

Conference

Conference	9th Annual Conference on Computational Learning Theory, COLT 1996
City	Desenzano del Garda, Italy
Period	6/28/96 → 7/1/96

All Science Journal Classification (ASJC) codes

Computational Mathematics

Access to Document

10.1145/238061.238090

Cite this

@inproceedings{ad5e94c78e0d4800b368dfa45cf35d75,

title = "Synthesizing enumeration techniques for language learning",

abstract = "This paper provides positive and negative results on algorithmically synthesizing, from grammars and from decision procedures for classes and languages, learning machines for identifying, from positive data, grammars for the languages in those classes. In the process, the uniformly decidable classes of recursive languages that can be behaviorally correctly identified from positive data are surprisingly characterized by Angluin's 1980 Condition 2 (the subset for principle for preventing over generalization).",

author = "Baliga, \{Ganesh R.\} and John Case and Sanjay Jain",

year = "1996",

month = jan,

day = "1",

doi = "10.1145/238061.238090",

language = "English (US)",

series = "Proceedings of the Annual ACM Conference on Computational Learning Theory",

pages = "169--180",

booktitle = "Proceedings of the ninth annual conference on Computational learning theory, COLT 1996",

note = "9th Annual Conference on Computational Learning Theory, COLT 1996 ; Conference date: 28-06-1996 Through 01-07-1996",

}

Baliga, GR, Case, J & Jain, S 1996, Synthesizing enumeration techniques for language learning. in Proceedings of the ninth annual conference on Computational learning theory, COLT 1996. Proceedings of the Annual ACM Conference on Computational Learning Theory, pp. 169-180, 9th Annual Conference on Computational Learning Theory, COLT 1996, Desenzano del Garda, Italy, 6/28/96. https://doi.org/10.1145/238061.238090

Synthesizing enumeration techniques for language learning. / Baliga, Ganesh R.; Case, John; Jain, Sanjay.
Proceedings of the ninth annual conference on Computational learning theory, COLT 1996. 1996. p. 169-180 (Proceedings of the Annual ACM Conference on Computational Learning Theory).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Synthesizing enumeration techniques for language learning

AU - Baliga, Ganesh R.

AU - Case, John

AU - Jain, Sanjay

PY - 1996/1/1

Y1 - 1996/1/1

N2 - This paper provides positive and negative results on algorithmically synthesizing, from grammars and from decision procedures for classes and languages, learning machines for identifying, from positive data, grammars for the languages in those classes. In the process, the uniformly decidable classes of recursive languages that can be behaviorally correctly identified from positive data are surprisingly characterized by Angluin's 1980 Condition 2 (the subset for principle for preventing over generalization).

AB - This paper provides positive and negative results on algorithmically synthesizing, from grammars and from decision procedures for classes and languages, learning machines for identifying, from positive data, grammars for the languages in those classes. In the process, the uniformly decidable classes of recursive languages that can be behaviorally correctly identified from positive data are surprisingly characterized by Angluin's 1980 Condition 2 (the subset for principle for preventing over generalization).

UR - https://www.scopus.com/pages/publications/0030388145

UR - https://www.scopus.com/pages/publications/0030388145#tab=citedBy

U2 - 10.1145/238061.238090

DO - 10.1145/238061.238090

M3 - Conference contribution

AN - SCOPUS:0030388145

T3 - Proceedings of the Annual ACM Conference on Computational Learning Theory

SP - 169

EP - 180

BT - Proceedings of the ninth annual conference on Computational learning theory, COLT 1996

T2 - 9th Annual Conference on Computational Learning Theory, COLT 1996

Y2 - 28 June 1996 through 1 July 1996

ER -

Synthesizing enumeration techniques for language learning

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this