Ontology-based protein-protein interactions extraction from literature using the hidden vector state model

Yulan He; Keiichi Nakata; Deyu Zhou

doi:10.1109/ICDMW.2008.11

Ontology-based protein-protein interactions extraction from literature using the hidden vector state model

Yulan He, Keiichi Nakata, Deyu Zhou

Computer Science Research Group

Research output: Chapter in Book/Published conference output › Other chapter contribution

Abstract

This paper proposes a novel framework of incorporating protein-protein interactions (PPI) ontology knowledge into PPI extraction from biomedical literature in order to address the emerging challenges of deep natural language understanding. It is built upon the existing work on relation extraction using the Hidden Vector State (HVS) model. The HVS model belongs to the category of statistical learning methods. It can be trained directly from un-annotated data in a constrained way whilst at the same time being able to capture the underlying named entity relationships. However, it is difficult to incorporate background knowledge or non-local information into the HVS model. This paper proposes to represent the HVS model as a conditionally trained undirected graphical model in which non-local features derived from PPI ontology through inference would be easily incorporated. The seamless fusion of ontology inference with statistical learning produces a new paradigm to information extraction.

Original language	English
Title of host publication	2008 IEEE international conference on data mining workshops
Publisher	IEEE
Pages	736-743
Number of pages	8
ISBN (Electronic)	978-0-7695-3503-6
DOIs	https://doi.org/10.1109/ICDMW.2008.11
Publication status	Published - 1 Jan 2008
Event	IEEE international conference on data mining workshops - Pisa, Italy Duration: 15 Dec 2008 → 19 Dec 2008

Conference

Conference	IEEE international conference on data mining workshops
Abbreviated title	ICDMW '08
Country/Territory	Italy
City	Pisa
Period	15/12/08 → 19/12/08

Bibliographical note

© 2008 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Keywords

hidden vector state model
PPI ontology
protein-protein interactions extraction
information extraction

Access to Document

10.1109/ICDMW.2008.11

Ontology-based protein-protein interactions extraction
© 2008 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 336 KB

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=4734001

Cite this

@inbook{15bc7112e4704b49ad6ca74744a02a80,

title = "Ontology-based protein-protein interactions extraction from literature using the hidden vector state model",

abstract = "This paper proposes a novel framework of incorporating protein-protein interactions (PPI) ontology knowledge into PPI extraction from biomedical literature in order to address the emerging challenges of deep natural language understanding. It is built upon the existing work on relation extraction using the Hidden Vector State (HVS) model. The HVS model belongs to the category of statistical learning methods. It can be trained directly from un-annotated data in a constrained way whilst at the same time being able to capture the underlying named entity relationships. However, it is difficult to incorporate background knowledge or non-local information into the HVS model. This paper proposes to represent the HVS model as a conditionally trained undirected graphical model in which non-local features derived from PPI ontology through inference would be easily incorporated. The seamless fusion of ontology inference with statistical learning produces a new paradigm to information extraction.",

keywords = "hidden vector state model, PPI ontology, protein-protein interactions extraction, information extraction",

author = "Yulan He and Keiichi Nakata and Deyu Zhou",

note = "{\textcopyright} 2008 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; IEEE international conference on data mining workshops, ICDMW '08 ; Conference date: 15-12-2008 Through 19-12-2008",

year = "2008",

month = jan,

day = "1",

doi = "10.1109/ICDMW.2008.11",

language = "English",

pages = "736--743",

booktitle = "2008 IEEE international conference on data mining workshops",

publisher = "IEEE",

address = "United States",

}

TY - CHAP

T1 - Ontology-based protein-protein interactions extraction from literature using the hidden vector state model

AU - He, Yulan

AU - Nakata, Keiichi

AU - Zhou, Deyu

N1 - © 2008 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2008/1/1

Y1 - 2008/1/1

N2 - This paper proposes a novel framework of incorporating protein-protein interactions (PPI) ontology knowledge into PPI extraction from biomedical literature in order to address the emerging challenges of deep natural language understanding. It is built upon the existing work on relation extraction using the Hidden Vector State (HVS) model. The HVS model belongs to the category of statistical learning methods. It can be trained directly from un-annotated data in a constrained way whilst at the same time being able to capture the underlying named entity relationships. However, it is difficult to incorporate background knowledge or non-local information into the HVS model. This paper proposes to represent the HVS model as a conditionally trained undirected graphical model in which non-local features derived from PPI ontology through inference would be easily incorporated. The seamless fusion of ontology inference with statistical learning produces a new paradigm to information extraction.

AB - This paper proposes a novel framework of incorporating protein-protein interactions (PPI) ontology knowledge into PPI extraction from biomedical literature in order to address the emerging challenges of deep natural language understanding. It is built upon the existing work on relation extraction using the Hidden Vector State (HVS) model. The HVS model belongs to the category of statistical learning methods. It can be trained directly from un-annotated data in a constrained way whilst at the same time being able to capture the underlying named entity relationships. However, it is difficult to incorporate background knowledge or non-local information into the HVS model. This paper proposes to represent the HVS model as a conditionally trained undirected graphical model in which non-local features derived from PPI ontology through inference would be easily incorporated. The seamless fusion of ontology inference with statistical learning produces a new paradigm to information extraction.

KW - hidden vector state model

KW - PPI ontology

KW - protein-protein interactions extraction

KW - information extraction

UR - http://www.scopus.com/inward/record.url?scp=62449205856&partnerID=8YFLogxK

U2 - 10.1109/ICDMW.2008.11

DO - 10.1109/ICDMW.2008.11

M3 - Other chapter contribution

AN - SCOPUS:62449205856

SP - 736

EP - 743

BT - 2008 IEEE international conference on data mining workshops

PB - IEEE

T2 - IEEE international conference on data mining workshops

Y2 - 15 December 2008 through 19 December 2008

ER -

Ontology-based protein-protein interactions extraction from literature using the hidden vector state model

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this