The reaserch of lable-mapping-based entity attribute extraction

Huilin Liu; Chen Chen; Liwei Zhang; Guoren Wang

doi:10.1109/PIC.2010.5687859

The reaserch of lable-mapping-based entity attribute extraction

Huilin Liu^*, Chen Chen, Liwei Zhang, Guoren Wang

^*Corresponding author for this work

Northeastern University China

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

With the rapid development of new media, such as computer and Internet, extract valuable entity attribute information from Web text can be significant. Aiming at this problem, this paper puts forward SALmap, this model calls seed method at first, which will create common candidate attribute label sets by defining data format rules. Then we construct the mapping relationship between the attributes and the labels using attribute value information and the maximum entropy model, and label the entity instance as well. Finally, hidden Markov model is applied to the relevant entity attribute extraction. Experiments prove SALmap model can significantly improve the precision and performance of entity attribute extraction.

Original language	English
Title of host publication	Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010
Pages	635-639
Number of pages	5
DOIs	https://doi.org/10.1109/PIC.2010.5687859
Publication status	Published - 2010
Externally published	Yes
Event	2010 1st IEEE International Conference on Progress in Informatics and Computing, PIC 2010 - Shanghai, China Duration: 10 Dec 2010 → 12 Dec 2010

Publication series

Name	Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010
Volume	1

Conference

Conference	2010 1st IEEE International Conference on Progress in Informatics and Computing, PIC 2010
Country/Territory	China
City	Shanghai
Period	10/12/10 → 12/12/10

Keywords

Attribute extraction
Attribute values
Hidden Markov model
Label mapping
Maximum entropy model

Access to Document

10.1109/PIC.2010.5687859

Cite this

Liu, H., Chen, C., Zhang, L., & Wang, G. (2010). The reaserch of lable-mapping-based entity attribute extraction. In Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010 (pp. 635-639). Article 5687859 (Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010; Vol. 1). https://doi.org/10.1109/PIC.2010.5687859

@inproceedings{7b428024197c46ec8791868762379d4e,

title = "The reaserch of lable-mapping-based entity attribute extraction",

abstract = "With the rapid development of new media, such as computer and Internet, extract valuable entity attribute information from Web text can be significant. Aiming at this problem, this paper puts forward SALmap, this model calls seed method at first, which will create common candidate attribute label sets by defining data format rules. Then we construct the mapping relationship between the attributes and the labels using attribute value information and the maximum entropy model, and label the entity instance as well. Finally, hidden Markov model is applied to the relevant entity attribute extraction. Experiments prove SALmap model can significantly improve the precision and performance of entity attribute extraction.",

keywords = "Attribute extraction, Attribute values, Hidden Markov model, Label mapping, Maximum entropy model",

author = "Huilin Liu and Chen Chen and Liwei Zhang and Guoren Wang",

year = "2010",

doi = "10.1109/PIC.2010.5687859",

language = "English",

isbn = "9781424467860",

series = "Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010",

pages = "635--639",

booktitle = "Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010",

note = "2010 1st IEEE International Conference on Progress in Informatics and Computing, PIC 2010 ; Conference date: 10-12-2010 Through 12-12-2010",

}

Liu, H, Chen, C, Zhang, L & Wang, G 2010, The reaserch of lable-mapping-based entity attribute extraction. in Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010., 5687859, Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010, vol. 1, pp. 635-639, 2010 1st IEEE International Conference on Progress in Informatics and Computing, PIC 2010, Shanghai, China, 10/12/10. https://doi.org/10.1109/PIC.2010.5687859

The reaserch of lable-mapping-based entity attribute extraction. / Liu, Huilin; Chen, Chen; Zhang, Liwei et al.
Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010. 2010. p. 635-639 5687859 (Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - The reaserch of lable-mapping-based entity attribute extraction

AU - Liu, Huilin

AU - Chen, Chen

AU - Zhang, Liwei

AU - Wang, Guoren

PY - 2010

Y1 - 2010

N2 - With the rapid development of new media, such as computer and Internet, extract valuable entity attribute information from Web text can be significant. Aiming at this problem, this paper puts forward SALmap, this model calls seed method at first, which will create common candidate attribute label sets by defining data format rules. Then we construct the mapping relationship between the attributes and the labels using attribute value information and the maximum entropy model, and label the entity instance as well. Finally, hidden Markov model is applied to the relevant entity attribute extraction. Experiments prove SALmap model can significantly improve the precision and performance of entity attribute extraction.

AB - With the rapid development of new media, such as computer and Internet, extract valuable entity attribute information from Web text can be significant. Aiming at this problem, this paper puts forward SALmap, this model calls seed method at first, which will create common candidate attribute label sets by defining data format rules. Then we construct the mapping relationship between the attributes and the labels using attribute value information and the maximum entropy model, and label the entity instance as well. Finally, hidden Markov model is applied to the relevant entity attribute extraction. Experiments prove SALmap model can significantly improve the precision and performance of entity attribute extraction.

KW - Attribute extraction

KW - Attribute values

KW - Hidden Markov model

KW - Label mapping

KW - Maximum entropy model

UR - https://www.scopus.com/pages/publications/79951475788

U2 - 10.1109/PIC.2010.5687859

DO - 10.1109/PIC.2010.5687859

M3 - Conference contribution

AN - SCOPUS:79951475788

SN - 9781424467860

T3 - Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010

SP - 635

EP - 639

BT - Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010

T2 - 2010 1st IEEE International Conference on Progress in Informatics and Computing, PIC 2010

Y2 - 10 December 2010 through 12 December 2010

ER -

Liu H, Chen C, Zhang L, Wang G. The reaserch of lable-mapping-based entity attribute extraction. In Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010. 2010. p. 635-639. 5687859. (Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC 2010). doi: 10.1109/PIC.2010.5687859

The reaserch of lable-mapping-based entity attribute extraction

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this