Investigation of weakly supervised learning for semantic role labeling

Joo Young Lee, Young In Song, Hae-Chang Rim

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

7 Citations (Scopus)

Abstract

In this paper, we investigate the possibility of the weakly supervised learning for Semantic Role Labeling. First, we attempt to achieve feature splitting which is the base constraint of co-training, and examine if co-training works for the task of Semantic Role Labeling. We also examine the possibility of self-training which uses the identical features with co-training, and compare the performance of cotraining and self-training. From the experiments, we found some interesting points about Semantic Role Labeling task and the weakly supervised learning. As far as we know, this is the first experiment to apply weakly supervised learning to Semantic Role Labeling and the experimental results show that Semantic Role Labeling can be successfully done by weakly supervised learning.

Original languageEnglish
Title of host publicationProceedings - ALPIT 2007 6th International Conference on Advanced Language Processing and Web Information Technology
Pages165-170
Number of pages6
DOIs
Publication statusPublished - 2007 Dec 1
Event6th International Conference on Advanced Language Processing and Web Information Technology, ALPIT 2007 - Luoyang, Henan, China
Duration: 2007 Aug 222007 Aug 24

Other

Other6th International Conference on Advanced Language Processing and Web Information Technology, ALPIT 2007
CountryChina
CityLuoyang, Henan
Period07/8/2207/8/24

Fingerprint

Supervised learning
Labeling
Semantics
Experiments

ASJC Scopus subject areas

  • Computer Science(all)
  • Information Systems

Cite this

Lee, J. Y., Song, Y. I., & Rim, H-C. (2007). Investigation of weakly supervised learning for semantic role labeling. In Proceedings - ALPIT 2007 6th International Conference on Advanced Language Processing and Web Information Technology (pp. 165-170). [4460634] https://doi.org/10.1109/ALPIT.2007.97

Investigation of weakly supervised learning for semantic role labeling. / Lee, Joo Young; Song, Young In; Rim, Hae-Chang.

Proceedings - ALPIT 2007 6th International Conference on Advanced Language Processing and Web Information Technology. 2007. p. 165-170 4460634.

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

Lee, JY, Song, YI & Rim, H-C 2007, Investigation of weakly supervised learning for semantic role labeling. in Proceedings - ALPIT 2007 6th International Conference on Advanced Language Processing and Web Information Technology., 4460634, pp. 165-170, 6th International Conference on Advanced Language Processing and Web Information Technology, ALPIT 2007, Luoyang, Henan, China, 07/8/22. https://doi.org/10.1109/ALPIT.2007.97
Lee JY, Song YI, Rim H-C. Investigation of weakly supervised learning for semantic role labeling. In Proceedings - ALPIT 2007 6th International Conference on Advanced Language Processing and Web Information Technology. 2007. p. 165-170. 4460634 https://doi.org/10.1109/ALPIT.2007.97
Lee, Joo Young ; Song, Young In ; Rim, Hae-Chang. / Investigation of weakly supervised learning for semantic role labeling. Proceedings - ALPIT 2007 6th International Conference on Advanced Language Processing and Web Information Technology. 2007. pp. 165-170
@inproceedings{da05728e84b14d1faf395652435af3f7,
title = "Investigation of weakly supervised learning for semantic role labeling",
abstract = "In this paper, we investigate the possibility of the weakly supervised learning for Semantic Role Labeling. First, we attempt to achieve feature splitting which is the base constraint of co-training, and examine if co-training works for the task of Semantic Role Labeling. We also examine the possibility of self-training which uses the identical features with co-training, and compare the performance of cotraining and self-training. From the experiments, we found some interesting points about Semantic Role Labeling task and the weakly supervised learning. As far as we know, this is the first experiment to apply weakly supervised learning to Semantic Role Labeling and the experimental results show that Semantic Role Labeling can be successfully done by weakly supervised learning.",
author = "Lee, {Joo Young} and Song, {Young In} and Hae-Chang Rim",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/ALPIT.2007.97",
language = "English",
isbn = "0769529305",
pages = "165--170",
booktitle = "Proceedings - ALPIT 2007 6th International Conference on Advanced Language Processing and Web Information Technology",

}

TY - GEN

T1 - Investigation of weakly supervised learning for semantic role labeling

AU - Lee, Joo Young

AU - Song, Young In

AU - Rim, Hae-Chang

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper, we investigate the possibility of the weakly supervised learning for Semantic Role Labeling. First, we attempt to achieve feature splitting which is the base constraint of co-training, and examine if co-training works for the task of Semantic Role Labeling. We also examine the possibility of self-training which uses the identical features with co-training, and compare the performance of cotraining and self-training. From the experiments, we found some interesting points about Semantic Role Labeling task and the weakly supervised learning. As far as we know, this is the first experiment to apply weakly supervised learning to Semantic Role Labeling and the experimental results show that Semantic Role Labeling can be successfully done by weakly supervised learning.

AB - In this paper, we investigate the possibility of the weakly supervised learning for Semantic Role Labeling. First, we attempt to achieve feature splitting which is the base constraint of co-training, and examine if co-training works for the task of Semantic Role Labeling. We also examine the possibility of self-training which uses the identical features with co-training, and compare the performance of cotraining and self-training. From the experiments, we found some interesting points about Semantic Role Labeling task and the weakly supervised learning. As far as we know, this is the first experiment to apply weakly supervised learning to Semantic Role Labeling and the experimental results show that Semantic Role Labeling can be successfully done by weakly supervised learning.

UR - http://www.scopus.com/inward/record.url?scp=50049092055&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50049092055&partnerID=8YFLogxK

U2 - 10.1109/ALPIT.2007.97

DO - 10.1109/ALPIT.2007.97

M3 - Conference contribution

AN - SCOPUS:50049092055

SN - 0769529305

SN - 9780769529301

SP - 165

EP - 170

BT - Proceedings - ALPIT 2007 6th International Conference on Advanced Language Processing and Web Information Technology

ER -