Toponym Extraction and Disambiguation Enhancement Using Loops of Feedback

Mena Badieh Habib, Maurice van Keulen

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

71 Downloads (Pure)

Abstract

Toponym extraction and disambiguation have received much attention in recent years. Typical fields addressing these topics are information retrieval, natural language processing, and semantic web. This paper addresses two problems with toponym extraction and disambiguation. First, almost no existing works examine the extraction and disambiguation interdependency. Second, existing disambiguation techniques mostly take as input extracted named entities without considering the uncertainty and imperfection of the extraction process. In this paper we aim to investigate both avenues and to show that explicit handling of the uncertainty of annotation has much potential for making both extraction and disambiguation more robust. We conducted experiments with a set of holiday home descriptions with the aim to extract and disambiguate toponyms. We show that the extraction confidence probabilities are useful in enhancing the effectiveness of disambiguation. Reciprocally, retraining the extraction models with information automatically derived from the disambiguation results, improves the extraction models. This mutual reinforcement is shown to even have an effect after several automatic iterations.
Original languageUndefined
Title of host publicationKnowledge Discovery, Knowledge Engineering and Knowledge Management: 4th International Joint Conference, IC3K 2012, Barcelona, Spain, October 4-7, 2012, Revised Selected Papers
EditorsA. Fred, J.L.G. Dietz, K. Liu, J. Filipe
Place of PublicationBerlin Heidelberg
PublisherSpringer
Pages113-129
Number of pages17
ISBN (Print)978-3-642-54104-9
DOIs
Publication statusPublished - 2013

Publication series

NameCommunications in Computer and Information Science
PublisherSpringer Verlag
Number415
Volume415
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Keywords

  • Toponym RecognitionToponym ExtractionToponym DisambiguationToponym LinkingUncertain Annotations
  • EWI-24610
  • Uncertain Annotations
  • IR-90489
  • Toponyms Extraction
  • METIS-304041
  • Toponym Disambiguation

Cite this

Habib, M. B., & van Keulen, M. (2013). Toponym Extraction and Disambiguation Enhancement Using Loops of Feedback. In A. Fred, J. L. G. Dietz, K. Liu, & J. Filipe (Eds.), Knowledge Discovery, Knowledge Engineering and Knowledge Management: 4th International Joint Conference, IC3K 2012, Barcelona, Spain, October 4-7, 2012, Revised Selected Papers (pp. 113-129). (Communications in Computer and Information Science; Vol. 415, No. 415). Berlin Heidelberg: Springer. https://doi.org/10.1007/978-3-642-54105-6_8
Habib, Mena Badieh ; van Keulen, Maurice. / Toponym Extraction and Disambiguation Enhancement Using Loops of Feedback. Knowledge Discovery, Knowledge Engineering and Knowledge Management: 4th International Joint Conference, IC3K 2012, Barcelona, Spain, October 4-7, 2012, Revised Selected Papers. editor / A. Fred ; J.L.G. Dietz ; K. Liu ; J. Filipe. Berlin Heidelberg : Springer, 2013. pp. 113-129 (Communications in Computer and Information Science; 415).
@inbook{83400bc93c6d44849f6d9ab22e807739,
title = "Toponym Extraction and Disambiguation Enhancement Using Loops of Feedback",
abstract = "Toponym extraction and disambiguation have received much attention in recent years. Typical fields addressing these topics are information retrieval, natural language processing, and semantic web. This paper addresses two problems with toponym extraction and disambiguation. First, almost no existing works examine the extraction and disambiguation interdependency. Second, existing disambiguation techniques mostly take as input extracted named entities without considering the uncertainty and imperfection of the extraction process. In this paper we aim to investigate both avenues and to show that explicit handling of the uncertainty of annotation has much potential for making both extraction and disambiguation more robust. We conducted experiments with a set of holiday home descriptions with the aim to extract and disambiguate toponyms. We show that the extraction confidence probabilities are useful in enhancing the effectiveness of disambiguation. Reciprocally, retraining the extraction models with information automatically derived from the disambiguation results, improves the extraction models. This mutual reinforcement is shown to even have an effect after several automatic iterations.",
keywords = "Toponym RecognitionToponym ExtractionToponym DisambiguationToponym LinkingUncertain Annotations, EWI-24610, Uncertain Annotations, IR-90489, Toponyms Extraction, METIS-304041, Toponym Disambiguation",
author = "Habib, {Mena Badieh} and {van Keulen}, Maurice",
note = "http://eprints.ewi.utwente.nl/24610",
year = "2013",
doi = "10.1007/978-3-642-54105-6_8",
language = "Undefined",
isbn = "978-3-642-54104-9",
series = "Communications in Computer and Information Science",
publisher = "Springer",
number = "415",
pages = "113--129",
editor = "A. Fred and J.L.G. Dietz and K. Liu and J. Filipe",
booktitle = "Knowledge Discovery, Knowledge Engineering and Knowledge Management: 4th International Joint Conference, IC3K 2012, Barcelona, Spain, October 4-7, 2012, Revised Selected Papers",

}

Habib, MB & van Keulen, M 2013, Toponym Extraction and Disambiguation Enhancement Using Loops of Feedback. in A Fred, JLG Dietz, K Liu & J Filipe (eds), Knowledge Discovery, Knowledge Engineering and Knowledge Management: 4th International Joint Conference, IC3K 2012, Barcelona, Spain, October 4-7, 2012, Revised Selected Papers. Communications in Computer and Information Science, no. 415, vol. 415, Springer, Berlin Heidelberg, pp. 113-129. https://doi.org/10.1007/978-3-642-54105-6_8

Toponym Extraction and Disambiguation Enhancement Using Loops of Feedback. / Habib, Mena Badieh; van Keulen, Maurice.

Knowledge Discovery, Knowledge Engineering and Knowledge Management: 4th International Joint Conference, IC3K 2012, Barcelona, Spain, October 4-7, 2012, Revised Selected Papers. ed. / A. Fred; J.L.G. Dietz; K. Liu; J. Filipe. Berlin Heidelberg : Springer, 2013. p. 113-129 (Communications in Computer and Information Science; Vol. 415, No. 415).

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

TY - CHAP

T1 - Toponym Extraction and Disambiguation Enhancement Using Loops of Feedback

AU - Habib, Mena Badieh

AU - van Keulen, Maurice

N1 - http://eprints.ewi.utwente.nl/24610

PY - 2013

Y1 - 2013

N2 - Toponym extraction and disambiguation have received much attention in recent years. Typical fields addressing these topics are information retrieval, natural language processing, and semantic web. This paper addresses two problems with toponym extraction and disambiguation. First, almost no existing works examine the extraction and disambiguation interdependency. Second, existing disambiguation techniques mostly take as input extracted named entities without considering the uncertainty and imperfection of the extraction process. In this paper we aim to investigate both avenues and to show that explicit handling of the uncertainty of annotation has much potential for making both extraction and disambiguation more robust. We conducted experiments with a set of holiday home descriptions with the aim to extract and disambiguate toponyms. We show that the extraction confidence probabilities are useful in enhancing the effectiveness of disambiguation. Reciprocally, retraining the extraction models with information automatically derived from the disambiguation results, improves the extraction models. This mutual reinforcement is shown to even have an effect after several automatic iterations.

AB - Toponym extraction and disambiguation have received much attention in recent years. Typical fields addressing these topics are information retrieval, natural language processing, and semantic web. This paper addresses two problems with toponym extraction and disambiguation. First, almost no existing works examine the extraction and disambiguation interdependency. Second, existing disambiguation techniques mostly take as input extracted named entities without considering the uncertainty and imperfection of the extraction process. In this paper we aim to investigate both avenues and to show that explicit handling of the uncertainty of annotation has much potential for making both extraction and disambiguation more robust. We conducted experiments with a set of holiday home descriptions with the aim to extract and disambiguate toponyms. We show that the extraction confidence probabilities are useful in enhancing the effectiveness of disambiguation. Reciprocally, retraining the extraction models with information automatically derived from the disambiguation results, improves the extraction models. This mutual reinforcement is shown to even have an effect after several automatic iterations.

KW - Toponym RecognitionToponym ExtractionToponym DisambiguationToponym LinkingUncertain Annotations

KW - EWI-24610

KW - Uncertain Annotations

KW - IR-90489

KW - Toponyms Extraction

KW - METIS-304041

KW - Toponym Disambiguation

U2 - 10.1007/978-3-642-54105-6_8

DO - 10.1007/978-3-642-54105-6_8

M3 - Chapter

SN - 978-3-642-54104-9

T3 - Communications in Computer and Information Science

SP - 113

EP - 129

BT - Knowledge Discovery, Knowledge Engineering and Knowledge Management: 4th International Joint Conference, IC3K 2012, Barcelona, Spain, October 4-7, 2012, Revised Selected Papers

A2 - Fred, A.

A2 - Dietz, J.L.G.

A2 - Liu, K.

A2 - Filipe, J.

PB - Springer

CY - Berlin Heidelberg

ER -

Habib MB, van Keulen M. Toponym Extraction and Disambiguation Enhancement Using Loops of Feedback. In Fred A, Dietz JLG, Liu K, Filipe J, editors, Knowledge Discovery, Knowledge Engineering and Knowledge Management: 4th International Joint Conference, IC3K 2012, Barcelona, Spain, October 4-7, 2012, Revised Selected Papers. Berlin Heidelberg: Springer. 2013. p. 113-129. (Communications in Computer and Information Science; 415). https://doi.org/10.1007/978-3-642-54105-6_8