Incremental information extraction using relational databases

Luis Tari, Phan Huy Tu, Jörg Hakenberg, Yi Chen, Tran Cao Son, Graciela Gonzalez, Chitta Baral

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Information extraction systems are traditionally implemented as a pipeline of special-purpose processing modules targeting the extraction of a particular kind of information. A major drawback of such an approach is that whenever a new extraction goal emerges or a module is improved, extraction has to be reapplied from scratch to the entire text corpus even though only a small part of the corpus might be affected. In this paper, we describe a novel approach for information extraction in which extraction needs are expressed in the form of database queries, which are evaluated and optimized by database systems. Using database queries for information extraction enables generic extraction and minimizes reprocessing of data by performing incremental extraction to identify which part of the data is affected by the change of components or goals. Furthermore, our approach provides automated query generation components so that casual users do not have to learn the query language in order to perform extraction. To demonstrate the feasibility of our incremental extraction approach, we performed experiments to highlight two important aspects of an information extraction system: efficiency and quality of extraction results. Our experiments show that in the event of deployment of a new module, our incremental extraction approach reduces the processing time by 89.64 percent as compared to a traditional pipeline approach. By applying our methods to a corpus of 17 million biomedical abstracts, our experiments show that the query performance is efficient for real-time applications. Our experiments also revealed that our approach achieves high quality extraction results.

Original languageEnglish (US)
Article number5611526
Pages (from-to)86-99
Number of pages14
JournalIEEE Transactions on Knowledge and Data Engineering
Volume24
Issue number1
DOIs
StatePublished - 2012

Fingerprint

Pipelines
Experiments
Query languages
Processing

Keywords

  • information storage and retrieval
  • query languages
  • Text mining

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Information Systems
  • Computer Science Applications

Cite this

Tari, L., Tu, P. H., Hakenberg, J., Chen, Y., Son, T. C., Gonzalez, G., & Baral, C. (2012). Incremental information extraction using relational databases. IEEE Transactions on Knowledge and Data Engineering, 24(1), 86-99. [5611526]. https://doi.org/10.1109/TKDE.2010.214

Incremental information extraction using relational databases. / Tari, Luis; Tu, Phan Huy; Hakenberg, Jörg; Chen, Yi; Son, Tran Cao; Gonzalez, Graciela; Baral, Chitta.

In: IEEE Transactions on Knowledge and Data Engineering, Vol. 24, No. 1, 5611526, 2012, p. 86-99.

Research output: Contribution to journalArticle

Tari, L, Tu, PH, Hakenberg, J, Chen, Y, Son, TC, Gonzalez, G & Baral, C 2012, 'Incremental information extraction using relational databases', IEEE Transactions on Knowledge and Data Engineering, vol. 24, no. 1, 5611526, pp. 86-99. https://doi.org/10.1109/TKDE.2010.214
Tari, Luis ; Tu, Phan Huy ; Hakenberg, Jörg ; Chen, Yi ; Son, Tran Cao ; Gonzalez, Graciela ; Baral, Chitta. / Incremental information extraction using relational databases. In: IEEE Transactions on Knowledge and Data Engineering. 2012 ; Vol. 24, No. 1. pp. 86-99.
@article{675669a4157b46a9bb62cbf90ae0672d,
title = "Incremental information extraction using relational databases",
abstract = "Information extraction systems are traditionally implemented as a pipeline of special-purpose processing modules targeting the extraction of a particular kind of information. A major drawback of such an approach is that whenever a new extraction goal emerges or a module is improved, extraction has to be reapplied from scratch to the entire text corpus even though only a small part of the corpus might be affected. In this paper, we describe a novel approach for information extraction in which extraction needs are expressed in the form of database queries, which are evaluated and optimized by database systems. Using database queries for information extraction enables generic extraction and minimizes reprocessing of data by performing incremental extraction to identify which part of the data is affected by the change of components or goals. Furthermore, our approach provides automated query generation components so that casual users do not have to learn the query language in order to perform extraction. To demonstrate the feasibility of our incremental extraction approach, we performed experiments to highlight two important aspects of an information extraction system: efficiency and quality of extraction results. Our experiments show that in the event of deployment of a new module, our incremental extraction approach reduces the processing time by 89.64 percent as compared to a traditional pipeline approach. By applying our methods to a corpus of 17 million biomedical abstracts, our experiments show that the query performance is efficient for real-time applications. Our experiments also revealed that our approach achieves high quality extraction results.",
keywords = "information storage and retrieval, query languages, Text mining",
author = "Luis Tari and Tu, {Phan Huy} and J{\"o}rg Hakenberg and Yi Chen and Son, {Tran Cao} and Graciela Gonzalez and Chitta Baral",
year = "2012",
doi = "10.1109/TKDE.2010.214",
language = "English (US)",
volume = "24",
pages = "86--99",
journal = "IEEE Transactions on Knowledge and Data Engineering",
issn = "1041-4347",
publisher = "IEEE Computer Society",
number = "1",

}

TY - JOUR

T1 - Incremental information extraction using relational databases

AU - Tari, Luis

AU - Tu, Phan Huy

AU - Hakenberg, Jörg

AU - Chen, Yi

AU - Son, Tran Cao

AU - Gonzalez, Graciela

AU - Baral, Chitta

PY - 2012

Y1 - 2012

N2 - Information extraction systems are traditionally implemented as a pipeline of special-purpose processing modules targeting the extraction of a particular kind of information. A major drawback of such an approach is that whenever a new extraction goal emerges or a module is improved, extraction has to be reapplied from scratch to the entire text corpus even though only a small part of the corpus might be affected. In this paper, we describe a novel approach for information extraction in which extraction needs are expressed in the form of database queries, which are evaluated and optimized by database systems. Using database queries for information extraction enables generic extraction and minimizes reprocessing of data by performing incremental extraction to identify which part of the data is affected by the change of components or goals. Furthermore, our approach provides automated query generation components so that casual users do not have to learn the query language in order to perform extraction. To demonstrate the feasibility of our incremental extraction approach, we performed experiments to highlight two important aspects of an information extraction system: efficiency and quality of extraction results. Our experiments show that in the event of deployment of a new module, our incremental extraction approach reduces the processing time by 89.64 percent as compared to a traditional pipeline approach. By applying our methods to a corpus of 17 million biomedical abstracts, our experiments show that the query performance is efficient for real-time applications. Our experiments also revealed that our approach achieves high quality extraction results.

AB - Information extraction systems are traditionally implemented as a pipeline of special-purpose processing modules targeting the extraction of a particular kind of information. A major drawback of such an approach is that whenever a new extraction goal emerges or a module is improved, extraction has to be reapplied from scratch to the entire text corpus even though only a small part of the corpus might be affected. In this paper, we describe a novel approach for information extraction in which extraction needs are expressed in the form of database queries, which are evaluated and optimized by database systems. Using database queries for information extraction enables generic extraction and minimizes reprocessing of data by performing incremental extraction to identify which part of the data is affected by the change of components or goals. Furthermore, our approach provides automated query generation components so that casual users do not have to learn the query language in order to perform extraction. To demonstrate the feasibility of our incremental extraction approach, we performed experiments to highlight two important aspects of an information extraction system: efficiency and quality of extraction results. Our experiments show that in the event of deployment of a new module, our incremental extraction approach reduces the processing time by 89.64 percent as compared to a traditional pipeline approach. By applying our methods to a corpus of 17 million biomedical abstracts, our experiments show that the query performance is efficient for real-time applications. Our experiments also revealed that our approach achieves high quality extraction results.

KW - information storage and retrieval

KW - query languages

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=82155181740&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82155181740&partnerID=8YFLogxK

U2 - 10.1109/TKDE.2010.214

DO - 10.1109/TKDE.2010.214

M3 - Article

AN - SCOPUS:82155181740

VL - 24

SP - 86

EP - 99

JO - IEEE Transactions on Knowledge and Data Engineering

JF - IEEE Transactions on Knowledge and Data Engineering

SN - 1041-4347

IS - 1

M1 - 5611526

ER -