Formal mechanisms for capturing regularizations

Adam Meyers; Ralph Grishman; Michiko Kosaka

Formal mechanisms for capturing regularizations

Adam Meyers, Ralph Grishman, Michiko Kosaka

Computer Science

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

Abstract

While initial treebanks and treebank parsers primarily involved surface analysis, recent work focuses on predicate argument (PA) structure. PA structure provides means to regularize variants (e.g., actives/passives) of sentences so that individual patterns may have better coverage (in MT, QA, IE, etc.), offsetting the sparse data problem. We encode such PA information in the GLARF framework. Our previous work discusses procedures for producing GLARF from treebanks and parsed data. This paper shows that GLARF is particularly well-suited for capturing regularization. We discuss crucial components of GLARF and demonstrate that other frameworks would require equivalent components to adequately express regularization.

Original language	English (US)
Pages	723-730
Number of pages	8
State	Published - 2002
Event	3rd International Conference on Language Resources and Evaluation, LREC 2002 - Las Palmas, Canary Islands, Spain Duration: May 29 2002 → May 31 2002

Other

Other	3rd International Conference on Language Resources and Evaluation, LREC 2002
Country/Territory	Spain
City	Las Palmas, Canary Islands
Period	5/29/02 → 5/31/02

ASJC Scopus subject areas

Linguistics and Language
Language and Linguistics
Education
Library and Information Sciences

Cite this

@conference{8e1c961d09fa4cc2a318c950942ec1d7,

title = "Formal mechanisms for capturing regularizations",

abstract = "While initial treebanks and treebank parsers primarily involved surface analysis, recent work focuses on predicate argument (PA) structure. PA structure provides means to regularize variants (e.g., actives/passives) of sentences so that individual patterns may have better coverage (in MT, QA, IE, etc.), offsetting the sparse data problem. We encode such PA information in the GLARF framework. Our previous work discusses procedures for producing GLARF from treebanks and parsed data. This paper shows that GLARF is particularly well-suited for capturing regularization. We discuss crucial components of GLARF and demonstrate that other frameworks would require equivalent components to adequately express regularization.",

author = "Adam Meyers and Ralph Grishman and Michiko Kosaka",

note = "Funding Information: This research was supported by the Defense Advanced Research Projects Agency under Grant N66001-00-1-8917 from the Space and Naval Warfare Systems Center, San Diego and by the National Science Foundation under Grant IIS-0081962.; 3rd International Conference on Language Resources and Evaluation, LREC 2002 ; Conference date: 29-05-2002 Through 31-05-2002",

year = "2002",

language = "English (US)",

pages = "723--730",

}

TY - CONF

T1 - Formal mechanisms for capturing regularizations

AU - Meyers, Adam

AU - Grishman, Ralph

AU - Kosaka, Michiko

N1 - Funding Information: This research was supported by the Defense Advanced Research Projects Agency under Grant N66001-00-1-8917 from the Space and Naval Warfare Systems Center, San Diego and by the National Science Foundation under Grant IIS-0081962.

PY - 2002

Y1 - 2002

N2 - While initial treebanks and treebank parsers primarily involved surface analysis, recent work focuses on predicate argument (PA) structure. PA structure provides means to regularize variants (e.g., actives/passives) of sentences so that individual patterns may have better coverage (in MT, QA, IE, etc.), offsetting the sparse data problem. We encode such PA information in the GLARF framework. Our previous work discusses procedures for producing GLARF from treebanks and parsed data. This paper shows that GLARF is particularly well-suited for capturing regularization. We discuss crucial components of GLARF and demonstrate that other frameworks would require equivalent components to adequately express regularization.

AB - While initial treebanks and treebank parsers primarily involved surface analysis, recent work focuses on predicate argument (PA) structure. PA structure provides means to regularize variants (e.g., actives/passives) of sentences so that individual patterns may have better coverage (in MT, QA, IE, etc.), offsetting the sparse data problem. We encode such PA information in the GLARF framework. Our previous work discusses procedures for producing GLARF from treebanks and parsed data. This paper shows that GLARF is particularly well-suited for capturing regularization. We discuss crucial components of GLARF and demonstrate that other frameworks would require equivalent components to adequately express regularization.

UR - http://www.scopus.com/inward/record.url?scp=33744830600&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33744830600&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:33744830600

SP - 723

EP - 730

T2 - 3rd International Conference on Language Resources and Evaluation, LREC 2002

Y2 - 29 May 2002 through 31 May 2002

ER -

Formal mechanisms for capturing regularizations

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this