Evolutional dependency parse trees for biological relation extraction

Hung Yu Kao, Yi Tsung Tang, Jian Fu Wang

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

2 Citations (Scopus)

Abstract

Due to the rapid growth in biological technology, the development of high-quality information extraction systems is needed and still remains a challenge. Several recently proposed approaches to biological relation extraction are based on machine learning techniques on lexical and syntactic information. Most use the dependency path between two genes/proteins instead of the whole dependency tree of a sentence for identifying relationships. However, the dependency path may not have any node between two entities. If a limited set of annotated training corpora is used for the construction of tree information of biological relationships, the training corpus will lack some sentence structures and cannot predict whether the sentence has a biological relationship. In this paper, we developed a biological relation extraction system called Evolutional Tree Extraction System - ETree. We extended the dependency path to the dependency subtree and developed a method that can automatically expand and prune these existing dependency subtrees into various dependency subtrees. These dependency subtrees are called "Evolutional Trees" and are used to predict the biological relationship sentences.

Original languageEnglish
Title of host publicationProceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011
Pages167-174
Number of pages8
DOIs
Publication statusPublished - 2011 Dec 27
Event2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011 - Taichung, Taiwan
Duration: 2011 Oct 242011 Oct 26

Publication series

NameProceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011

Other

Other2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011
CountryTaiwan
CityTaichung
Period11-10-2411-10-26

Fingerprint

Syntactics
Learning systems
Genes
Proteins

All Science Journal Classification (ASJC) codes

  • Bioengineering
  • Biomedical Engineering

Cite this

Kao, H. Y., Tang, Y. T., & Wang, J. F. (2011). Evolutional dependency parse trees for biological relation extraction. In Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011 (pp. 167-174). [6089824] (Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011). https://doi.org/10.1109/BIBE.2011.33
Kao, Hung Yu ; Tang, Yi Tsung ; Wang, Jian Fu. / Evolutional dependency parse trees for biological relation extraction. Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011. 2011. pp. 167-174 (Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011).
@inproceedings{dbd7f13203da44ab8feb402f03726a93,
title = "Evolutional dependency parse trees for biological relation extraction",
abstract = "Due to the rapid growth in biological technology, the development of high-quality information extraction systems is needed and still remains a challenge. Several recently proposed approaches to biological relation extraction are based on machine learning techniques on lexical and syntactic information. Most use the dependency path between two genes/proteins instead of the whole dependency tree of a sentence for identifying relationships. However, the dependency path may not have any node between two entities. If a limited set of annotated training corpora is used for the construction of tree information of biological relationships, the training corpus will lack some sentence structures and cannot predict whether the sentence has a biological relationship. In this paper, we developed a biological relation extraction system called Evolutional Tree Extraction System - ETree. We extended the dependency path to the dependency subtree and developed a method that can automatically expand and prune these existing dependency subtrees into various dependency subtrees. These dependency subtrees are called {"}Evolutional Trees{"} and are used to predict the biological relationship sentences.",
author = "Kao, {Hung Yu} and Tang, {Yi Tsung} and Wang, {Jian Fu}",
year = "2011",
month = "12",
day = "27",
doi = "10.1109/BIBE.2011.33",
language = "English",
isbn = "9780769543918",
series = "Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011",
pages = "167--174",
booktitle = "Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011",

}

Kao, HY, Tang, YT & Wang, JF 2011, Evolutional dependency parse trees for biological relation extraction. in Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011., 6089824, Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011, pp. 167-174, 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011, Taichung, Taiwan, 11-10-24. https://doi.org/10.1109/BIBE.2011.33

Evolutional dependency parse trees for biological relation extraction. / Kao, Hung Yu; Tang, Yi Tsung; Wang, Jian Fu.

Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011. 2011. p. 167-174 6089824 (Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011).

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

TY - GEN

T1 - Evolutional dependency parse trees for biological relation extraction

AU - Kao, Hung Yu

AU - Tang, Yi Tsung

AU - Wang, Jian Fu

PY - 2011/12/27

Y1 - 2011/12/27

N2 - Due to the rapid growth in biological technology, the development of high-quality information extraction systems is needed and still remains a challenge. Several recently proposed approaches to biological relation extraction are based on machine learning techniques on lexical and syntactic information. Most use the dependency path between two genes/proteins instead of the whole dependency tree of a sentence for identifying relationships. However, the dependency path may not have any node between two entities. If a limited set of annotated training corpora is used for the construction of tree information of biological relationships, the training corpus will lack some sentence structures and cannot predict whether the sentence has a biological relationship. In this paper, we developed a biological relation extraction system called Evolutional Tree Extraction System - ETree. We extended the dependency path to the dependency subtree and developed a method that can automatically expand and prune these existing dependency subtrees into various dependency subtrees. These dependency subtrees are called "Evolutional Trees" and are used to predict the biological relationship sentences.

AB - Due to the rapid growth in biological technology, the development of high-quality information extraction systems is needed and still remains a challenge. Several recently proposed approaches to biological relation extraction are based on machine learning techniques on lexical and syntactic information. Most use the dependency path between two genes/proteins instead of the whole dependency tree of a sentence for identifying relationships. However, the dependency path may not have any node between two entities. If a limited set of annotated training corpora is used for the construction of tree information of biological relationships, the training corpus will lack some sentence structures and cannot predict whether the sentence has a biological relationship. In this paper, we developed a biological relation extraction system called Evolutional Tree Extraction System - ETree. We extended the dependency path to the dependency subtree and developed a method that can automatically expand and prune these existing dependency subtrees into various dependency subtrees. These dependency subtrees are called "Evolutional Trees" and are used to predict the biological relationship sentences.

UR - http://www.scopus.com/inward/record.url?scp=84155191310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84155191310&partnerID=8YFLogxK

U2 - 10.1109/BIBE.2011.33

DO - 10.1109/BIBE.2011.33

M3 - Conference contribution

AN - SCOPUS:84155191310

SN - 9780769543918

T3 - Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011

SP - 167

EP - 174

BT - Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011

ER -

Kao HY, Tang YT, Wang JF. Evolutional dependency parse trees for biological relation extraction. In Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011. 2011. p. 167-174. 6089824. (Proceedings - 2011 11th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2011). https://doi.org/10.1109/BIBE.2011.33