Conjunctive structure detection in Chinese Q&A system

Shixi Fan; Xuan Wang; Xiaolong Wang

Conjunctive structure detection in Chinese Q&A system

Shixi Fan^*
, Xuan Wang
, Xiaolong Wang

^*Corresponding author for this work

Harbin Institute of Technology Shenzhen

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

Abstract

We propose a SVM (Support Vector Machine) based approach to detect and annotate conjunctive structures in a Chinese Q&A system. The SVM model implements a simple and efficient method, which transfer the conjunctive detection problem into a labeling problem. The training data is 23000 sentences and the testing data is 3000 sentences. The best Result: Precision is 93.15%, Recall is 93.65%. These results show that the proposed method is effective in conjunctive structures detection.

Original language	English
Pages (from-to)	891-898
Number of pages	8
Journal	Journal of Computational Information Systems
Volume	4
Issue number	3
State	Published - Jun 2008
Externally published	Yes

Keywords

Conjunctive structure
Q&A
SVM

Cite this

@article{f981230eff334ca2ba0a8adb921555b0,

title = "Conjunctive structure detection in Chinese Q\&A system",

abstract = "We propose a SVM (Support Vector Machine) based approach to detect and annotate conjunctive structures in a Chinese Q\&A system. The SVM model implements a simple and efficient method, which transfer the conjunctive detection problem into a labeling problem. The training data is 23000 sentences and the testing data is 3000 sentences. The best Result: Precision is 93.15\%, Recall is 93.65\%. These results show that the proposed method is effective in conjunctive structures detection.",

keywords = "Conjunctive structure, Q\&A, SVM",

author = "Shixi Fan and Xuan Wang and Xiaolong Wang",

year = "2008",

month = jun,

language = "英语",

volume = "4",

pages = "891--898",

journal = "Journal of Computational Information Systems",

issn = "1553-9105",

publisher = "Binary Information Press",

number = "3",

}

TY - JOUR

T1 - Conjunctive structure detection in Chinese Q&A system

AU - Fan, Shixi

AU - Wang, Xuan

AU - Wang, Xiaolong

PY - 2008/6

Y1 - 2008/6

N2 - We propose a SVM (Support Vector Machine) based approach to detect and annotate conjunctive structures in a Chinese Q&A system. The SVM model implements a simple and efficient method, which transfer the conjunctive detection problem into a labeling problem. The training data is 23000 sentences and the testing data is 3000 sentences. The best Result: Precision is 93.15%, Recall is 93.65%. These results show that the proposed method is effective in conjunctive structures detection.

AB - We propose a SVM (Support Vector Machine) based approach to detect and annotate conjunctive structures in a Chinese Q&A system. The SVM model implements a simple and efficient method, which transfer the conjunctive detection problem into a labeling problem. The training data is 23000 sentences and the testing data is 3000 sentences. The best Result: Precision is 93.15%, Recall is 93.65%. These results show that the proposed method is effective in conjunctive structures detection.

KW - Conjunctive structure

KW - Q&A

KW - SVM

UR - https://www.scopus.com/pages/publications/48549101314

M3 - 文章

AN - SCOPUS:48549101314

SN - 1553-9105

VL - 4

SP - 891

EP - 898

JO - Journal of Computational Information Systems

JF - Journal of Computational Information Systems

IS - 3

ER -

Conjunctive structure detection in Chinese Q&A system

Abstract

Keywords

Other files and links

Fingerprint

Cite this