Use of Deep Linguistic Features for the Recognition and Labeling of Semantic Arguments

John Chen; Owen Rambow

doi:10.3115/1119355.1119361

Use of Deep Linguistic Features for the Recognition and Labeling of Semantic Arguments

John Chen
, Owen Rambow

Linguistics

Columbia University

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

62 Scopus citations

Abstract

We use deep linguistic features to predict semantic roles on syntactic arguments, and show that these perform considerably better than surface-oriented features. We also show that predicting labels from a “lightweight” parser that generates deep syntactic features performs comparably to using a full parser that generates only surface syntactic features.

Original language	English
Pages	41-48
Number of pages	8
DOIs	https://doi.org/10.3115/1119355.1119361
State	Published - 2003
Event	8th Conference on Empirical Methods in Natural Language Processing, EMNLP 2003 - Sapporo, Japan Duration: Jul 11 2003 → Jul 12 2003

Conference

Conference	8th Conference on Empirical Methods in Natural Language Processing, EMNLP 2003
Country/Territory	Japan
City	Sapporo
Period	07/11/03 → 07/12/03

Access to Document

10.3115/1119355.1119361

Cite this

@conference{863a683d6344442a8d6835a03202ee57,

title = "Use of Deep Linguistic Features for the Recognition and Labeling of Semantic Arguments",

abstract = "We use deep linguistic features to predict semantic roles on syntactic arguments, and show that these perform considerably better than surface-oriented features. We also show that predicting labels from a “lightweight” parser that generates deep syntactic features performs comparably to using a full parser that generates only surface syntactic features.",

author = "John Chen and Owen Rambow",

note = "Publisher Copyright: {\textcopyright} 2003 EMNLP. All Rights Reserved.; 8th Conference on Empirical Methods in Natural Language Processing, EMNLP 2003 ; Conference date: 11-07-2003 Through 12-07-2003",

year = "2003",

doi = "10.3115/1119355.1119361",

language = "English",

pages = "41--48",

}

TY - CONF

T1 - Use of Deep Linguistic Features for the Recognition and Labeling of Semantic Arguments

AU - Chen, John

AU - Rambow, Owen

PY - 2003

Y1 - 2003

N2 - We use deep linguistic features to predict semantic roles on syntactic arguments, and show that these perform considerably better than surface-oriented features. We also show that predicting labels from a “lightweight” parser that generates deep syntactic features performs comparably to using a full parser that generates only surface syntactic features.

AB - We use deep linguistic features to predict semantic roles on syntactic arguments, and show that these perform considerably better than surface-oriented features. We also show that predicting labels from a “lightweight” parser that generates deep syntactic features performs comparably to using a full parser that generates only surface syntactic features.

UR - https://www.scopus.com/pages/publications/85146433133

U2 - 10.3115/1119355.1119361

DO - 10.3115/1119355.1119361

M3 - Paper

AN - SCOPUS:85146433133

SP - 41

EP - 48

T2 - 8th Conference on Empirical Methods in Natural Language Processing, EMNLP 2003

Y2 - 11 July 2003 through 12 July 2003

ER -

Use of Deep Linguistic Features for the Recognition and Labeling of Semantic Arguments

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this