Partially lexicalized parsing model utilizing rich features

So Young Park, Yong Jae Kwak, Joon Ho Lim, Hae-Chang Rim, Soo Hong Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, we propose a partially lexicalized parsing model utilizing rich features to improve the parsing ability and reduce the parsing cost. In order to disambiguate parse trees effectively, it employs several useful features such as a syntactic label feature, a content feature, a functional feature, and a size feature. Besides, it is partially lexicalized so as to reduce the parsing cost closely connected with lexical information. Moreover, it is designed to be suitable for representing word order variation and constituent ellipsis in Korean sentences. Experimental results show that the proposed parsing model using more features performs better although it less depends on lexical information.

Original languageEnglish
Title of host publication8th International Conference on Spoken Language Processing, ICSLP 2004
PublisherInternational Speech Communication Association
Pages2201-2204
Number of pages4
Publication statusPublished - 2004
Event8th International Conference on Spoken Language Processing, ICSLP 2004 - Jeju, Jeju Island, Korea, Republic of
Duration: 2004 Oct 42004 Oct 8

Other

Other8th International Conference on Spoken Language Processing, ICSLP 2004
CountryKorea, Republic of
CityJeju, Jeju Island
Period04/10/404/10/8

Fingerprint

costs
ability
Parsing
Costs
Syntax
Ellipse
Constituent

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Park, S. Y., Kwak, Y. J., Lim, J. H., Rim, H-C., & Kim, S. H. (2004). Partially lexicalized parsing model utilizing rich features. In 8th International Conference on Spoken Language Processing, ICSLP 2004 (pp. 2201-2204). International Speech Communication Association.

Partially lexicalized parsing model utilizing rich features. / Park, So Young; Kwak, Yong Jae; Lim, Joon Ho; Rim, Hae-Chang; Kim, Soo Hong.

8th International Conference on Spoken Language Processing, ICSLP 2004. International Speech Communication Association, 2004. p. 2201-2204.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Park, SY, Kwak, YJ, Lim, JH, Rim, H-C & Kim, SH 2004, Partially lexicalized parsing model utilizing rich features. in 8th International Conference on Spoken Language Processing, ICSLP 2004. International Speech Communication Association, pp. 2201-2204, 8th International Conference on Spoken Language Processing, ICSLP 2004, Jeju, Jeju Island, Korea, Republic of, 04/10/4.
Park SY, Kwak YJ, Lim JH, Rim H-C, Kim SH. Partially lexicalized parsing model utilizing rich features. In 8th International Conference on Spoken Language Processing, ICSLP 2004. International Speech Communication Association. 2004. p. 2201-2204
Park, So Young ; Kwak, Yong Jae ; Lim, Joon Ho ; Rim, Hae-Chang ; Kim, Soo Hong. / Partially lexicalized parsing model utilizing rich features. 8th International Conference on Spoken Language Processing, ICSLP 2004. International Speech Communication Association, 2004. pp. 2201-2204
@inproceedings{17979012ee2a4ecd8fdda9b6a560b22f,
title = "Partially lexicalized parsing model utilizing rich features",
abstract = "In this paper, we propose a partially lexicalized parsing model utilizing rich features to improve the parsing ability and reduce the parsing cost. In order to disambiguate parse trees effectively, it employs several useful features such as a syntactic label feature, a content feature, a functional feature, and a size feature. Besides, it is partially lexicalized so as to reduce the parsing cost closely connected with lexical information. Moreover, it is designed to be suitable for representing word order variation and constituent ellipsis in Korean sentences. Experimental results show that the proposed parsing model using more features performs better although it less depends on lexical information.",
author = "Park, {So Young} and Kwak, {Yong Jae} and Lim, {Joon Ho} and Hae-Chang Rim and Kim, {Soo Hong}",
year = "2004",
language = "English",
pages = "2201--2204",
booktitle = "8th International Conference on Spoken Language Processing, ICSLP 2004",
publisher = "International Speech Communication Association",

}

TY - GEN

T1 - Partially lexicalized parsing model utilizing rich features

AU - Park, So Young

AU - Kwak, Yong Jae

AU - Lim, Joon Ho

AU - Rim, Hae-Chang

AU - Kim, Soo Hong

PY - 2004

Y1 - 2004

N2 - In this paper, we propose a partially lexicalized parsing model utilizing rich features to improve the parsing ability and reduce the parsing cost. In order to disambiguate parse trees effectively, it employs several useful features such as a syntactic label feature, a content feature, a functional feature, and a size feature. Besides, it is partially lexicalized so as to reduce the parsing cost closely connected with lexical information. Moreover, it is designed to be suitable for representing word order variation and constituent ellipsis in Korean sentences. Experimental results show that the proposed parsing model using more features performs better although it less depends on lexical information.

AB - In this paper, we propose a partially lexicalized parsing model utilizing rich features to improve the parsing ability and reduce the parsing cost. In order to disambiguate parse trees effectively, it employs several useful features such as a syntactic label feature, a content feature, a functional feature, and a size feature. Besides, it is partially lexicalized so as to reduce the parsing cost closely connected with lexical information. Moreover, it is designed to be suitable for representing word order variation and constituent ellipsis in Korean sentences. Experimental results show that the proposed parsing model using more features performs better although it less depends on lexical information.

UR - http://www.scopus.com/inward/record.url?scp=33745565578&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745565578&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33745565578

SP - 2201

EP - 2204

BT - 8th International Conference on Spoken Language Processing, ICSLP 2004

PB - International Speech Communication Association

ER -