Augmenting and Efficiently Utilizing Domain Theory in Explanation-Based Natural Language Acquisition

Rey Long Liu; Von Wun Soo

doi:10.1016/B978-1-55860-247-2.50041-3

Augmenting and Efficiently Utilizing Domain Theory in Explanation-Based Natural Language Acquisition

Rey Long Liu, Von Wun Soo

National Tsing Hua University

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

4 Scopus citations

Abstract

In this paper, a new language acquisition model is proposed to acquire parsing-related knowledge via an Explanation-Based Learning (EBL) approach. The domain theory in the model consists of two parts: a static part and a dynamic part. The static part consists of the universal linguistic principles proposed in the Generalized Phrase Structure Grammar (GPSG) formalism, while the dynamic part contains the Context-Free grammar rules as well as syntactic and thematic features of lexicons. In parsing (problem-solving), both parts work together to parse input sentences, and in learning, the dynamic part is enriched and generalized by obeying the principles in the static part To be a robust and practical system, the model also incorporates the concepts of knowledge indexing, common work sharing, and dynamic conflict resolution to maintain efficiency of the problem solving module. The effect of these problem solving strategies to the knowledge utility problem in machine learning is thus investigated based on the experiments of the language acquisition model.

Original language	English
Title of host publication	Proceedings of the 9th International Workshop on Machine Learning, ICML 1992
Editors	Derek H. Sleeman, Peter Edwards
Publisher	Morgan Kaufmann Publishers, Inc.
Pages	282-289
Number of pages	8
ISBN (Electronic)	155860247X, 9781558602472
DOIs	https://doi.org/10.1016/B978-1-55860-247-2.50041-3
State	Published - 1992
Externally published	Yes
Event	9th International Conference on Machine Learning, ICML 1992 - Aberdeen, United Kingdom Duration: 01 07 1992 → 03 07 1992

Publication series

Name	Proceedings of the 9th International Workshop on Machine Learning, ICML 1992

Conference

Conference	9th International Conference on Machine Learning, ICML 1992
Country/Territory	United Kingdom
City	Aberdeen
Period	01/07/92 → 03/07/92

Bibliographical note

Publisher Copyright:
© 1992 Proceedings of the 9th International Workshop on Machine Learning, ICML 1992. All rights reserved.

Access to Document

10.1016/B978-1-55860-247-2.50041-3

Cite this

Liu, R. L., & Soo, V. W. (1992). Augmenting and Efficiently Utilizing Domain Theory in Explanation-Based Natural Language Acquisition. In D. H. Sleeman, & P. Edwards (Eds.), Proceedings of the 9th International Workshop on Machine Learning, ICML 1992 (pp. 282-289). (Proceedings of the 9th International Workshop on Machine Learning, ICML 1992). Morgan Kaufmann Publishers, Inc.. https://doi.org/10.1016/B978-1-55860-247-2.50041-3

Liu, Rey Long ; Soo, Von Wun. / Augmenting and Efficiently Utilizing Domain Theory in Explanation-Based Natural Language Acquisition. Proceedings of the 9th International Workshop on Machine Learning, ICML 1992. editor / Derek H. Sleeman ; Peter Edwards. Morgan Kaufmann Publishers, Inc., 1992. pp. 282-289 (Proceedings of the 9th International Workshop on Machine Learning, ICML 1992).

@inproceedings{cc132cd3b68147d2a17c27c79650686a,

title = "Augmenting and Efficiently Utilizing Domain Theory in Explanation-Based Natural Language Acquisition",

abstract = "In this paper, a new language acquisition model is proposed to acquire parsing-related knowledge via an Explanation-Based Learning (EBL) approach. The domain theory in the model consists of two parts: a static part and a dynamic part. The static part consists of the universal linguistic principles proposed in the Generalized Phrase Structure Grammar (GPSG) formalism, while the dynamic part contains the Context-Free grammar rules as well as syntactic and thematic features of lexicons. In parsing (problem-solving), both parts work together to parse input sentences, and in learning, the dynamic part is enriched and generalized by obeying the principles in the static part To be a robust and practical system, the model also incorporates the concepts of knowledge indexing, common work sharing, and dynamic conflict resolution to maintain efficiency of the problem solving module. The effect of these problem solving strategies to the knowledge utility problem in machine learning is thus investigated based on the experiments of the language acquisition model.",

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

note = "Publisher Copyright: {\textcopyright} 1992 Proceedings of the 9th International Workshop on Machine Learning, ICML 1992. All rights reserved.; 9th International Conference on Machine Learning, ICML 1992 ; Conference date: 01-07-1992 Through 03-07-1992",

year = "1992",

doi = "10.1016/B978-1-55860-247-2.50041-3",

language = "英语",

series = "Proceedings of the 9th International Workshop on Machine Learning, ICML 1992",

publisher = "Morgan Kaufmann Publishers, Inc.",

pages = "282--289",

editor = "Sleeman, {Derek H.} and Peter Edwards",

booktitle = "Proceedings of the 9th International Workshop on Machine Learning, ICML 1992",

}

Liu, RL & Soo, VW 1992, Augmenting and Efficiently Utilizing Domain Theory in Explanation-Based Natural Language Acquisition. in DH Sleeman & P Edwards (eds), Proceedings of the 9th International Workshop on Machine Learning, ICML 1992. Proceedings of the 9th International Workshop on Machine Learning, ICML 1992, Morgan Kaufmann Publishers, Inc., pp. 282-289, 9th International Conference on Machine Learning, ICML 1992, Aberdeen, United Kingdom, 01/07/92. https://doi.org/10.1016/B978-1-55860-247-2.50041-3

Augmenting and Efficiently Utilizing Domain Theory in Explanation-Based Natural Language Acquisition. / Liu, Rey Long; Soo, Von Wun.
Proceedings of the 9th International Workshop on Machine Learning, ICML 1992. ed. / Derek H. Sleeman; Peter Edwards. Morgan Kaufmann Publishers, Inc., 1992. p. 282-289 (Proceedings of the 9th International Workshop on Machine Learning, ICML 1992).

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

TY - GEN

T1 - Augmenting and Efficiently Utilizing Domain Theory in Explanation-Based Natural Language Acquisition

AU - Liu, Rey Long

AU - Soo, Von Wun

PY - 1992

Y1 - 1992

N2 - In this paper, a new language acquisition model is proposed to acquire parsing-related knowledge via an Explanation-Based Learning (EBL) approach. The domain theory in the model consists of two parts: a static part and a dynamic part. The static part consists of the universal linguistic principles proposed in the Generalized Phrase Structure Grammar (GPSG) formalism, while the dynamic part contains the Context-Free grammar rules as well as syntactic and thematic features of lexicons. In parsing (problem-solving), both parts work together to parse input sentences, and in learning, the dynamic part is enriched and generalized by obeying the principles in the static part To be a robust and practical system, the model also incorporates the concepts of knowledge indexing, common work sharing, and dynamic conflict resolution to maintain efficiency of the problem solving module. The effect of these problem solving strategies to the knowledge utility problem in machine learning is thus investigated based on the experiments of the language acquisition model.

AB - In this paper, a new language acquisition model is proposed to acquire parsing-related knowledge via an Explanation-Based Learning (EBL) approach. The domain theory in the model consists of two parts: a static part and a dynamic part. The static part consists of the universal linguistic principles proposed in the Generalized Phrase Structure Grammar (GPSG) formalism, while the dynamic part contains the Context-Free grammar rules as well as syntactic and thematic features of lexicons. In parsing (problem-solving), both parts work together to parse input sentences, and in learning, the dynamic part is enriched and generalized by obeying the principles in the static part To be a robust and practical system, the model also incorporates the concepts of knowledge indexing, common work sharing, and dynamic conflict resolution to maintain efficiency of the problem solving module. The effect of these problem solving strategies to the knowledge utility problem in machine learning is thus investigated based on the experiments of the language acquisition model.

UR - http://www.scopus.com/inward/record.url?scp=85028809486&partnerID=8YFLogxK

U2 - 10.1016/B978-1-55860-247-2.50041-3

DO - 10.1016/B978-1-55860-247-2.50041-3

M3 - 会议稿件

AN - SCOPUS:85028809486

T3 - Proceedings of the 9th International Workshop on Machine Learning, ICML 1992

SP - 282

EP - 289

BT - Proceedings of the 9th International Workshop on Machine Learning, ICML 1992

A2 - Sleeman, Derek H.

A2 - Edwards, Peter

PB - Morgan Kaufmann Publishers, Inc.

T2 - 9th International Conference on Machine Learning, ICML 1992

Y2 - 1 July 1992 through 3 July 1992

ER -

Liu RL, Soo VW. Augmenting and Efficiently Utilizing Domain Theory in Explanation-Based Natural Language Acquisition. In Sleeman DH, Edwards P, editors, Proceedings of the 9th International Workshop on Machine Learning, ICML 1992. Morgan Kaufmann Publishers, Inc. 1992. p. 282-289. (Proceedings of the 9th International Workshop on Machine Learning, ICML 1992). doi: 10.1016/B978-1-55860-247-2.50041-3

Augmenting and Efficiently Utilizing Domain Theory in Explanation-Based Natural Language Acquisition

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this