Automatic extraction of microorganisms and their habitats from free text using text mining workflows.

Balakrishna Kolluru; Sirintra Nakjang; Robert P. Hirt; Anil Wipat; Sophia Ananiadou

Automatic extraction of microorganisms and their habitats from free text using text mining workflows.

Balakrishna Kolluru, Sirintra Nakjang, Robert P. Hirt, Anil Wipat, Sophia Ananiadou

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

Abstract

In this paper we illustrate the usage of text mining workflows to automatically extract instances of microorganisms and their habitats from free text; these entries can then be curated and added to different databases. To this end, we use a Conditional Random Field (CRF) based classifier, as part of the workflows, to extract the mention of microorganisms, habitats and the inter-relation between organisms and their habitats. Results indicate a good performance for extraction of microorganisms and the relation extraction aspects of the task (with a precision of over 80%), while habitat recognition is only moderate (a precision of about 65%). We also conjecture that pdf-to-text conversion can be quite noisy and this implicitly affects any sentence-based relation extraction algorithms.

Original language	English
Title of host publication	Journal of integrative bioinformatics\|J Integr Bioinform
Pages	184
Volume	8
Publication status	Published - 2011
Event	International Symposium on Integrative Bioinformatics - Duration: 1 Jan 1824 → …

Conference

Conference	International Symposium on Integrative Bioinformatics
Period	1/01/24 → …

Cite this

@inproceedings{a7ea0ac988374255aef1402f838dbfb2,

title = "Automatic extraction of microorganisms and their habitats from free text using text mining workflows.",

abstract = "In this paper we illustrate the usage of text mining workflows to automatically extract instances of microorganisms and their habitats from free text; these entries can then be curated and added to different databases. To this end, we use a Conditional Random Field (CRF) based classifier, as part of the workflows, to extract the mention of microorganisms, habitats and the inter-relation between organisms and their habitats. Results indicate a good performance for extraction of microorganisms and the relation extraction aspects of the task (with a precision of over 80%), while habitat recognition is only moderate (a precision of about 65%). We also conjecture that pdf-to-text conversion can be quite noisy and this implicitly affects any sentence-based relation extraction algorithms.",

author = "Balakrishna Kolluru and Sirintra Nakjang and Hirt, {Robert P.} and Anil Wipat and Sophia Ananiadou",

year = "2011",

language = "English",

volume = "8",

pages = "184",

booktitle = "Journal of integrative bioinformatics|J Integr Bioinform",

note = "International Symposium on Integrative Bioinformatics ; Conference date: 01-01-1824",

}

TY - GEN

T1 - Automatic extraction of microorganisms and their habitats from free text using text mining workflows.

AU - Kolluru, Balakrishna

AU - Nakjang, Sirintra

AU - Hirt, Robert P.

AU - Wipat, Anil

AU - Ananiadou, Sophia

PY - 2011

Y1 - 2011

N2 - In this paper we illustrate the usage of text mining workflows to automatically extract instances of microorganisms and their habitats from free text; these entries can then be curated and added to different databases. To this end, we use a Conditional Random Field (CRF) based classifier, as part of the workflows, to extract the mention of microorganisms, habitats and the inter-relation between organisms and their habitats. Results indicate a good performance for extraction of microorganisms and the relation extraction aspects of the task (with a precision of over 80%), while habitat recognition is only moderate (a precision of about 65%). We also conjecture that pdf-to-text conversion can be quite noisy and this implicitly affects any sentence-based relation extraction algorithms.

AB - In this paper we illustrate the usage of text mining workflows to automatically extract instances of microorganisms and their habitats from free text; these entries can then be curated and added to different databases. To this end, we use a Conditional Random Field (CRF) based classifier, as part of the workflows, to extract the mention of microorganisms, habitats and the inter-relation between organisms and their habitats. Results indicate a good performance for extraction of microorganisms and the relation extraction aspects of the task (with a precision of over 80%), while habitat recognition is only moderate (a precision of about 65%). We also conjecture that pdf-to-text conversion can be quite noisy and this implicitly affects any sentence-based relation extraction algorithms.

M3 - Conference contribution

VL - 8

SP - 184

BT - Journal of integrative bioinformatics|J Integr Bioinform

T2 - International Symposium on Integrative Bioinformatics

Y2 - 1 January 1824

ER -

Automatic extraction of microorganisms and their habitats from free text using text mining workflows.

Abstract

Conference

Fingerprint

Cite this