Finding Difficult-to-Disambiguate Words

Towards an Efficient Workflow to Implement Word Sense Disambiguation

Manabu Torii, Jung Wei Fan, Daniel S. Zisook

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

Abstract

In the biomedical and clinical domain, valuable information is frequently represented in free-text documents. Natural language processing (NLP) is a powerful tool that can extract structured information from theses documents. Word sense disambiguation (WSD) is a critical component in an NLP pipeline that increases the accuracy of the extracted information. However, WSD is expensive to apply for all known ambiguous words. Given limited time and resources, one practical strategy is to prioritize easy-to-disambiguate words and efficiently maximize the coverage of disambiguation. To aid prioritization efforts, we studied two quantitative indicators that are associated with how easy/difficult it is to disambiguate any given word.

Original languageEnglish (US)
Title of host publicationProceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015
EditorsWai-Tat Fu, Prabhakaran Balakrishnan, Sanda Harabagiu, Fei Wang, Jaideep Srivatsava
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages1
ISBN (Electronic)9781467395489
DOIs
StatePublished - Dec 8 2015
Externally publishedYes
Event3rd IEEE International Conference on Healthcare Informatics, ICHI 2015 - Dallas, United States
Duration: Oct 21 2015Oct 23 2015

Other

Other3rd IEEE International Conference on Healthcare Informatics, ICHI 2015
CountryUnited States
CityDallas
Period10/21/1510/23/15

Fingerprint

Natural Language Processing
Workflow

Keywords

  • Medical Informatics
  • Natural Language Processing
  • Word Sense Disambiguation

ASJC Scopus subject areas

  • Health Informatics

Cite this

Torii, M., Fan, J. W., & Zisook, D. S. (2015). Finding Difficult-to-Disambiguate Words: Towards an Efficient Workflow to Implement Word Sense Disambiguation. In W-T. Fu, P. Balakrishnan, S. Harabagiu, F. Wang, & J. Srivatsava (Eds.), Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015 [7349727] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHI.2015.66

Finding Difficult-to-Disambiguate Words : Towards an Efficient Workflow to Implement Word Sense Disambiguation. / Torii, Manabu; Fan, Jung Wei; Zisook, Daniel S.

Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015. ed. / Wai-Tat Fu; Prabhakaran Balakrishnan; Sanda Harabagiu; Fei Wang; Jaideep Srivatsava. Institute of Electrical and Electronics Engineers Inc., 2015. 7349727.

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

Torii, M, Fan, JW & Zisook, DS 2015, Finding Difficult-to-Disambiguate Words: Towards an Efficient Workflow to Implement Word Sense Disambiguation. in W-T Fu, P Balakrishnan, S Harabagiu, F Wang & J Srivatsava (eds), Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015., 7349727, Institute of Electrical and Electronics Engineers Inc., 3rd IEEE International Conference on Healthcare Informatics, ICHI 2015, Dallas, United States, 10/21/15. https://doi.org/10.1109/ICHI.2015.66
Torii M, Fan JW, Zisook DS. Finding Difficult-to-Disambiguate Words: Towards an Efficient Workflow to Implement Word Sense Disambiguation. In Fu W-T, Balakrishnan P, Harabagiu S, Wang F, Srivatsava J, editors, Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015. Institute of Electrical and Electronics Engineers Inc. 2015. 7349727 https://doi.org/10.1109/ICHI.2015.66
Torii, Manabu ; Fan, Jung Wei ; Zisook, Daniel S. / Finding Difficult-to-Disambiguate Words : Towards an Efficient Workflow to Implement Word Sense Disambiguation. Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015. editor / Wai-Tat Fu ; Prabhakaran Balakrishnan ; Sanda Harabagiu ; Fei Wang ; Jaideep Srivatsava. Institute of Electrical and Electronics Engineers Inc., 2015.
@inproceedings{0e96dcc12b414165a04dff1c0c4af51f,
title = "Finding Difficult-to-Disambiguate Words: Towards an Efficient Workflow to Implement Word Sense Disambiguation",
abstract = "In the biomedical and clinical domain, valuable information is frequently represented in free-text documents. Natural language processing (NLP) is a powerful tool that can extract structured information from theses documents. Word sense disambiguation (WSD) is a critical component in an NLP pipeline that increases the accuracy of the extracted information. However, WSD is expensive to apply for all known ambiguous words. Given limited time and resources, one practical strategy is to prioritize easy-to-disambiguate words and efficiently maximize the coverage of disambiguation. To aid prioritization efforts, we studied two quantitative indicators that are associated with how easy/difficult it is to disambiguate any given word.",
keywords = "Medical Informatics, Natural Language Processing, Word Sense Disambiguation",
author = "Manabu Torii and Fan, {Jung Wei} and Zisook, {Daniel S.}",
year = "2015",
month = "12",
day = "8",
doi = "10.1109/ICHI.2015.66",
language = "English (US)",
editor = "Wai-Tat Fu and Prabhakaran Balakrishnan and Sanda Harabagiu and Fei Wang and Jaideep Srivatsava",
booktitle = "Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Finding Difficult-to-Disambiguate Words

T2 - Towards an Efficient Workflow to Implement Word Sense Disambiguation

AU - Torii, Manabu

AU - Fan, Jung Wei

AU - Zisook, Daniel S.

PY - 2015/12/8

Y1 - 2015/12/8

N2 - In the biomedical and clinical domain, valuable information is frequently represented in free-text documents. Natural language processing (NLP) is a powerful tool that can extract structured information from theses documents. Word sense disambiguation (WSD) is a critical component in an NLP pipeline that increases the accuracy of the extracted information. However, WSD is expensive to apply for all known ambiguous words. Given limited time and resources, one practical strategy is to prioritize easy-to-disambiguate words and efficiently maximize the coverage of disambiguation. To aid prioritization efforts, we studied two quantitative indicators that are associated with how easy/difficult it is to disambiguate any given word.

AB - In the biomedical and clinical domain, valuable information is frequently represented in free-text documents. Natural language processing (NLP) is a powerful tool that can extract structured information from theses documents. Word sense disambiguation (WSD) is a critical component in an NLP pipeline that increases the accuracy of the extracted information. However, WSD is expensive to apply for all known ambiguous words. Given limited time and resources, one practical strategy is to prioritize easy-to-disambiguate words and efficiently maximize the coverage of disambiguation. To aid prioritization efforts, we studied two quantitative indicators that are associated with how easy/difficult it is to disambiguate any given word.

KW - Medical Informatics

KW - Natural Language Processing

KW - Word Sense Disambiguation

UR - http://www.scopus.com/inward/record.url?scp=84966277133&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966277133&partnerID=8YFLogxK

U2 - 10.1109/ICHI.2015.66

DO - 10.1109/ICHI.2015.66

M3 - Conference contribution

BT - Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015

A2 - Fu, Wai-Tat

A2 - Balakrishnan, Prabhakaran

A2 - Harabagiu, Sanda

A2 - Wang, Fei

A2 - Srivatsava, Jaideep

PB - Institute of Electrical and Electronics Engineers Inc.

ER -