基于词模式嵌入的词语上下位关系分类

Jiawei Sun; Zhenghua Li; Wenliang Chen; Min Zhang

doi:10.13209/j.0479-8023.2018.055

基于词模式嵌入的词语上下位关系分类

Translated title of the contribution: Hypernym Relation Classification Based on Word Pattern

Jiawei Sun
, Zhenghua Li^*
, Wenliang Chen
, Min Zhang

^*Corresponding author for this work

Soochow University

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

The authors propose a hypernym relation classification method based on word pattern, which can effectively alleviate the sparsity problem suffered by the traditional path-based method. Furthermore, this paper makes an effective combination of the path-based method and the distributional method via word pattern embedding. To demonstrate the effectiveness of the proposed approach, the authors manually annotated a Chinese hypernym dataset containing 12000 word pairs. The experimental results show that the proposed word pattern embedding approach is effective and can achieve an F1 score of 95.36%.

Translated title of the contribution	Hypernym Relation Classification Based on Word Pattern
Original language	Chinese (Traditional)
Pages (from-to)	1-7
Number of pages	7
Journal	Beijing Daxue Xuebao (Ziran Kexue Ban)/Acta Scientiarum Naturalium Universitatis Pekinensis
Volume	55
Issue number	1
DOIs	https://doi.org/10.13209/j.0479-8023.2018.055
State	Published - 20 Jan 2019
Externally published	Yes

Access to Document

10.13209/j.0479-8023.2018.055

Cite this

@article{9966219a51424438b333c8facff50e5c,

title = "基于词模式嵌入的词语上下位关系分类",

abstract = "The authors propose a hypernym relation classification method based on word pattern, which can effectively alleviate the sparsity problem suffered by the traditional path-based method. Furthermore, this paper makes an effective combination of the path-based method and the distributional method via word pattern embedding. To demonstrate the effectiveness of the proposed approach, the authors manually annotated a Chinese hypernym dataset containing 12000 word pairs. The experimental results show that the proposed word pattern embedding approach is effective and can achieve an F1 score of 95.36\%.",

keywords = "Hypernym relation classification, Word embedding, Word pattern, Word pattern embedding",

author = "Jiawei Sun and Zhenghua Li and Wenliang Chen and Min Zhang",

note = "Publisher Copyright: {\textcopyright} 2019 Peking University.",

year = "2019",

month = jan,

day = "20",

doi = "10.13209/j.0479-8023.2018.055",

language = "繁体中文",

volume = "55",

pages = "1--7",

journal = "Beijing Daxue Xuebao (Ziran Kexue Ban)/Acta Scientiarum Naturalium Universitatis Pekinensis",

issn = "0479-8023",

publisher = "Peking University",

number = "1",

}

TY - JOUR

T1 - 基于词模式嵌入的词语上下位关系分类

AU - Sun, Jiawei

AU - Li, Zhenghua

AU - Chen, Wenliang

AU - Zhang, Min

PY - 2019/1/20

Y1 - 2019/1/20

N2 - The authors propose a hypernym relation classification method based on word pattern, which can effectively alleviate the sparsity problem suffered by the traditional path-based method. Furthermore, this paper makes an effective combination of the path-based method and the distributional method via word pattern embedding. To demonstrate the effectiveness of the proposed approach, the authors manually annotated a Chinese hypernym dataset containing 12000 word pairs. The experimental results show that the proposed word pattern embedding approach is effective and can achieve an F1 score of 95.36%.

AB - The authors propose a hypernym relation classification method based on word pattern, which can effectively alleviate the sparsity problem suffered by the traditional path-based method. Furthermore, this paper makes an effective combination of the path-based method and the distributional method via word pattern embedding. To demonstrate the effectiveness of the proposed approach, the authors manually annotated a Chinese hypernym dataset containing 12000 word pairs. The experimental results show that the proposed word pattern embedding approach is effective and can achieve an F1 score of 95.36%.

KW - Hypernym relation classification

KW - Word embedding

KW - Word pattern

KW - Word pattern embedding

UR - https://www.scopus.com/pages/publications/85062998617

U2 - 10.13209/j.0479-8023.2018.055

DO - 10.13209/j.0479-8023.2018.055

M3 - 文章

AN - SCOPUS:85062998617

SN - 0479-8023

VL - 55

SP - 1

EP - 7

JO - Beijing Daxue Xuebao (Ziran Kexue Ban)/Acta Scientiarum Naturalium Universitatis Pekinensis

JF - Beijing Daxue Xuebao (Ziran Kexue Ban)/Acta Scientiarum Naturalium Universitatis Pekinensis

IS - 1

ER -

基于词模式嵌入的词语上下位关系分类

Abstract

Access to Document

Other files and links

Fingerprint

Cite this