Japanese semantic role labeling with hierarchical tag context trees

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

Abstract

In this paper we describe that the hierarchical tag context tree (HTCT) approach improves the accuracy of semantic role labeling on Japanese text. In Japanese language there are functional multiword expressions such as no-tame-ni and yotte that have potential to designate semantic relations between a predicate and its arguments. Since these expressions come to the end part of each argument, the performance of the CRF-based semantic role labeler can be improved by taking into account the last morphemes of each argument as features. We apply our proposed system to the annotated corpus of semantic role labels on a balanced Japanese corpus. The experimental results show that the CRFbased labeler with features extracted by HTCT approach outperforms the normal CRF-based labeler.

Original languageEnglish
Title of host publicationCommunications in Computer and Information Science
PublisherSpringer Verlag
Pages21-32
Number of pages12
Volume593
ISBN (Print)9789811005145
DOIs
Publication statusPublished - 2016
Event14th International Conference of the Pacific Association for Computaitonal Linguistics, PACLING 2015 - Bali, Indonesia
Duration: May 19 2015May 21 2015

Publication series

NameCommunications in Computer and Information Science
Volume593
ISSN (Print)18650929

Other

Other14th International Conference of the Pacific Association for Computaitonal Linguistics, PACLING 2015
CountryIndonesia
CityBali
Period5/19/155/21/15

Fingerprint

Labeling
Semantics
Labels

Keywords

  • CRFs
  • Hierarchical tag context trees
  • Semantic role labeling

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Ishihara, Y., & Takeuchi, K. (2016). Japanese semantic role labeling with hierarchical tag context trees. In Communications in Computer and Information Science (Vol. 593, pp. 21-32). (Communications in Computer and Information Science; Vol. 593). Springer Verlag. https://doi.org/10.1007/978-981-10-0515-2_2

Japanese semantic role labeling with hierarchical tag context trees. / Ishihara, Yasuhiro; Takeuchi, Koichi.

Communications in Computer and Information Science. Vol. 593 Springer Verlag, 2016. p. 21-32 (Communications in Computer and Information Science; Vol. 593).

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

Ishihara, Y & Takeuchi, K 2016, Japanese semantic role labeling with hierarchical tag context trees. in Communications in Computer and Information Science. vol. 593, Communications in Computer and Information Science, vol. 593, Springer Verlag, pp. 21-32, 14th International Conference of the Pacific Association for Computaitonal Linguistics, PACLING 2015, Bali, Indonesia, 5/19/15. https://doi.org/10.1007/978-981-10-0515-2_2
Ishihara Y, Takeuchi K. Japanese semantic role labeling with hierarchical tag context trees. In Communications in Computer and Information Science. Vol. 593. Springer Verlag. 2016. p. 21-32. (Communications in Computer and Information Science). https://doi.org/10.1007/978-981-10-0515-2_2
Ishihara, Yasuhiro ; Takeuchi, Koichi. / Japanese semantic role labeling with hierarchical tag context trees. Communications in Computer and Information Science. Vol. 593 Springer Verlag, 2016. pp. 21-32 (Communications in Computer and Information Science).
@inproceedings{0a4daa9662124bae8bcc3f11658c204d,
title = "Japanese semantic role labeling with hierarchical tag context trees",
abstract = "In this paper we describe that the hierarchical tag context tree (HTCT) approach improves the accuracy of semantic role labeling on Japanese text. In Japanese language there are functional multiword expressions such as no-tame-ni and yotte that have potential to designate semantic relations between a predicate and its arguments. Since these expressions come to the end part of each argument, the performance of the CRF-based semantic role labeler can be improved by taking into account the last morphemes of each argument as features. We apply our proposed system to the annotated corpus of semantic role labels on a balanced Japanese corpus. The experimental results show that the CRFbased labeler with features extracted by HTCT approach outperforms the normal CRF-based labeler.",
keywords = "CRFs, Hierarchical tag context trees, Semantic role labeling",
author = "Yasuhiro Ishihara and Koichi Takeuchi",
year = "2016",
doi = "10.1007/978-981-10-0515-2_2",
language = "English",
isbn = "9789811005145",
volume = "593",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "21--32",
booktitle = "Communications in Computer and Information Science",

}

TY - GEN

T1 - Japanese semantic role labeling with hierarchical tag context trees

AU - Ishihara, Yasuhiro

AU - Takeuchi, Koichi

PY - 2016

Y1 - 2016

N2 - In this paper we describe that the hierarchical tag context tree (HTCT) approach improves the accuracy of semantic role labeling on Japanese text. In Japanese language there are functional multiword expressions such as no-tame-ni and yotte that have potential to designate semantic relations between a predicate and its arguments. Since these expressions come to the end part of each argument, the performance of the CRF-based semantic role labeler can be improved by taking into account the last morphemes of each argument as features. We apply our proposed system to the annotated corpus of semantic role labels on a balanced Japanese corpus. The experimental results show that the CRFbased labeler with features extracted by HTCT approach outperforms the normal CRF-based labeler.

AB - In this paper we describe that the hierarchical tag context tree (HTCT) approach improves the accuracy of semantic role labeling on Japanese text. In Japanese language there are functional multiword expressions such as no-tame-ni and yotte that have potential to designate semantic relations between a predicate and its arguments. Since these expressions come to the end part of each argument, the performance of the CRF-based semantic role labeler can be improved by taking into account the last morphemes of each argument as features. We apply our proposed system to the annotated corpus of semantic role labels on a balanced Japanese corpus. The experimental results show that the CRFbased labeler with features extracted by HTCT approach outperforms the normal CRF-based labeler.

KW - CRFs

KW - Hierarchical tag context trees

KW - Semantic role labeling

UR - http://www.scopus.com/inward/record.url?scp=84961194105&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961194105&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-0515-2_2

DO - 10.1007/978-981-10-0515-2_2

M3 - Conference contribution

AN - SCOPUS:84961194105

SN - 9789811005145

VL - 593

T3 - Communications in Computer and Information Science

SP - 21

EP - 32

BT - Communications in Computer and Information Science

PB - Springer Verlag

ER -