Acquisition of unbounded dependency using explanation-based learning

Rey Long Liu; Von Wun Soo

Acquisition of unbounded dependency using explanation-based learning

Rey Long Liu, Von Wun Soo

National Tsing Hua University

Research output: Contribution to conference › Conference Paper › peer-review

1 Scopus citations

Abstract

A natural language acquisition model using Explanation-Based Learning (EBL) had been proposed to acquire parsing-related knowledge which includes Context-Free grammar rules and syntactic and thematic features of lexicons. The domain theory that is assumed to be innate to the model includes the theta-theory and the universal feature instantiation principles in Generalized Phrase Structure Grammar (GPSG). In this paper, we show in particular how unbounded dependency may be acquired in the natural language acquisition model. The acquisition problem of unbounded dependency may be further divided into two sub-problems: detecting whether there are moved constituents and finding the places to which the constituents are moved. For these problems, the universal innate domain theory facilitates and constrains the acquisition process which is otherwise intractable.

Original language	English
Pages	99-119
Number of pages	21
State	Published - 1992
Externally published	Yes
Event	5th Computational Linguistics Conference, ROCLING 1992 - Taipei, Taiwan Duration: 01 09 1992 → …

Conference

Conference	5th Computational Linguistics Conference, ROCLING 1992
Country/Territory	Taiwan
City	Taipei
Period	01/09/92 → …

Bibliographical note

Publisher Copyright:
© 1992 Proceedings of Rocling 5th Computational Linguistics Conference, ROCLING 1992. All rights reserved.

Keywords

Explanation-based learning
Knowledge assimilation
Natural language acquisition
Theta theory
Universal feature instantiation principles

Cite this

@conference{3f9d3179f35d4ca387b99e0ce135df31,

title = "Acquisition of unbounded dependency using explanation-based learning",

abstract = "A natural language acquisition model using Explanation-Based Learning (EBL) had been proposed to acquire parsing-related knowledge which includes Context-Free grammar rules and syntactic and thematic features of lexicons. The domain theory that is assumed to be innate to the model includes the theta-theory and the universal feature instantiation principles in Generalized Phrase Structure Grammar (GPSG). In this paper, we show in particular how unbounded dependency may be acquired in the natural language acquisition model. The acquisition problem of unbounded dependency may be further divided into two sub-problems: detecting whether there are moved constituents and finding the places to which the constituents are moved. For these problems, the universal innate domain theory facilitates and constrains the acquisition process which is otherwise intractable.",

keywords = "Explanation-based learning, Knowledge assimilation, Natural language acquisition, Theta theory, Universal feature instantiation principles",

author = "Liu, {Rey Long} and Soo, {Von Wun}",

note = "Publisher Copyright: {\textcopyright} 1992 Proceedings of Rocling 5th Computational Linguistics Conference, ROCLING 1992. All rights reserved.; 5th Computational Linguistics Conference, ROCLING 1992 ; Conference date: 01-09-1992",

year = "1992",

language = "英语",

pages = "99--119",

}

TY - CONF

T1 - Acquisition of unbounded dependency using explanation-based learning

AU - Liu, Rey Long

AU - Soo, Von Wun

PY - 1992

Y1 - 1992

N2 - A natural language acquisition model using Explanation-Based Learning (EBL) had been proposed to acquire parsing-related knowledge which includes Context-Free grammar rules and syntactic and thematic features of lexicons. The domain theory that is assumed to be innate to the model includes the theta-theory and the universal feature instantiation principles in Generalized Phrase Structure Grammar (GPSG). In this paper, we show in particular how unbounded dependency may be acquired in the natural language acquisition model. The acquisition problem of unbounded dependency may be further divided into two sub-problems: detecting whether there are moved constituents and finding the places to which the constituents are moved. For these problems, the universal innate domain theory facilitates and constrains the acquisition process which is otherwise intractable.

AB - A natural language acquisition model using Explanation-Based Learning (EBL) had been proposed to acquire parsing-related knowledge which includes Context-Free grammar rules and syntactic and thematic features of lexicons. The domain theory that is assumed to be innate to the model includes the theta-theory and the universal feature instantiation principles in Generalized Phrase Structure Grammar (GPSG). In this paper, we show in particular how unbounded dependency may be acquired in the natural language acquisition model. The acquisition problem of unbounded dependency may be further divided into two sub-problems: detecting whether there are moved constituents and finding the places to which the constituents are moved. For these problems, the universal innate domain theory facilitates and constrains the acquisition process which is otherwise intractable.

KW - Explanation-based learning

KW - Knowledge assimilation

KW - Natural language acquisition

KW - Theta theory

KW - Universal feature instantiation principles

UR - http://www.scopus.com/inward/record.url?scp=0343014329&partnerID=8YFLogxK

M3 - 论文

AN - SCOPUS:0343014329

SP - 99

EP - 119

T2 - 5th Computational Linguistics Conference, ROCLING 1992

Y2 - 1 September 1992

ER -

Acquisition of unbounded dependency using explanation-based learning

Abstract

Conference

Bibliographical note

Keywords

Other files and links

Fingerprint

Cite this