Feeding a Gazetteer: Leveraging word embeddings for toponym mining

Sinai Rusinek; Nitzan Gado

doi:10.1145/3486187.3490202

Feeding a Gazetteer: Leveraging word embeddings for toponym mining

Sinai Rusinek, Nitzan Gado

Department of Jewish History

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

Abstract

We propose a workflow for retrieving place names from a corpus of Hebrew historical newspapers. We show that using an initial curated set of unambiguous toponyms and vector similarity is a productive method to populate a gazetteer with previously unknown variant names of known places, as well as names of places which are not yet included in the Gazetteer. We examine several parameters for enhancing accuracy and suggest a workflow that combines computation with human expertise, and is valuable to spatial history as well as to other domains.

Original language	English
Title of host publication	Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021
Editors	Ludovic Moncla, Carmen Brando, Katherine McDonough
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450391023
DOIs	https://doi.org/10.1145/3486187.3490202
State	Published - 2 Nov 2021
Event	5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021 - Beijing, China Duration: 2 Nov 2021 → …

Publication series

Name	Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021

Conference

Conference	5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021
Country/Territory	China
City	Beijing
Period	2/11/21 → …

Bibliographical note

Publisher Copyright:
© 2021 Owner/Author.

Keywords

Gazetteers
Historical Newspapers
Natural Language Processing
Toponym extraction
Word Embeddings

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Information Systems

Access to Document

10.1145/3486187.3490202

Cite this

Rusinek, S., & Gado, N. (2021). Feeding a Gazetteer: Leveraging word embeddings for toponym mining. In L. Moncla, C. Brando, & K. McDonough (Eds.), Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021 (Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021). Association for Computing Machinery, Inc. https://doi.org/10.1145/3486187.3490202

Rusinek, Sinai ; Gado, Nitzan. / Feeding a Gazetteer : Leveraging word embeddings for toponym mining. Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021. editor / Ludovic Moncla ; Carmen Brando ; Katherine McDonough. Association for Computing Machinery, Inc, 2021. (Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021).

@inproceedings{f9785d2240f3448f970c36cb6b47ee4b,

title = "Feeding a Gazetteer: Leveraging word embeddings for toponym mining",

abstract = "We propose a workflow for retrieving place names from a corpus of Hebrew historical newspapers. We show that using an initial curated set of unambiguous toponyms and vector similarity is a productive method to populate a gazetteer with previously unknown variant names of known places, as well as names of places which are not yet included in the Gazetteer. We examine several parameters for enhancing accuracy and suggest a workflow that combines computation with human expertise, and is valuable to spatial history as well as to other domains.",

keywords = "Gazetteers, Historical Newspapers, Natural Language Processing, Toponym extraction, Word Embeddings",

author = "Sinai Rusinek and Nitzan Gado",

note = "Publisher Copyright: {\textcopyright} 2021 Owner/Author.; 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021 ; Conference date: 02-11-2021",

year = "2021",

month = nov,

day = "2",

doi = "10.1145/3486187.3490202",

language = "English",

series = "Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021",

publisher = "Association for Computing Machinery, Inc",

editor = "Ludovic Moncla and Carmen Brando and Katherine McDonough",

booktitle = "Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021",

}

Rusinek, S & Gado, N 2021, Feeding a Gazetteer: Leveraging word embeddings for toponym mining. in L Moncla, C Brando & K McDonough (eds), Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021. Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021, Association for Computing Machinery, Inc, 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021, Beijing, China, 2/11/21. https://doi.org/10.1145/3486187.3490202

Feeding a Gazetteer: Leveraging word embeddings for toponym mining. / Rusinek, Sinai; Gado, Nitzan.
Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021. ed. / Ludovic Moncla; Carmen Brando; Katherine McDonough. Association for Computing Machinery, Inc, 2021. (Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021).

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

TY - GEN

T1 - Feeding a Gazetteer

T2 - 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021

AU - Rusinek, Sinai

AU - Gado, Nitzan

PY - 2021/11/2

Y1 - 2021/11/2

N2 - We propose a workflow for retrieving place names from a corpus of Hebrew historical newspapers. We show that using an initial curated set of unambiguous toponyms and vector similarity is a productive method to populate a gazetteer with previously unknown variant names of known places, as well as names of places which are not yet included in the Gazetteer. We examine several parameters for enhancing accuracy and suggest a workflow that combines computation with human expertise, and is valuable to spatial history as well as to other domains.

AB - We propose a workflow for retrieving place names from a corpus of Hebrew historical newspapers. We show that using an initial curated set of unambiguous toponyms and vector similarity is a productive method to populate a gazetteer with previously unknown variant names of known places, as well as names of places which are not yet included in the Gazetteer. We examine several parameters for enhancing accuracy and suggest a workflow that combines computation with human expertise, and is valuable to spatial history as well as to other domains.

KW - Gazetteers

KW - Historical Newspapers

KW - Natural Language Processing

KW - Toponym extraction

KW - Word Embeddings

UR - http://www.scopus.com/inward/record.url?scp=85119251720&partnerID=8YFLogxK

U2 - 10.1145/3486187.3490202

DO - 10.1145/3486187.3490202

M3 - Conference contribution

AN - SCOPUS:85119251720

T3 - Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021

BT - Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021

A2 - Moncla, Ludovic

A2 - Brando, Carmen

A2 - McDonough, Katherine

PB - Association for Computing Machinery, Inc

Y2 - 2 November 2021

ER -

Rusinek S, Gado N. Feeding a Gazetteer: Leveraging word embeddings for toponym mining. In Moncla L, Brando C, McDonough K, editors, Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021. Association for Computing Machinery, Inc. 2021. (Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021). doi: 10.1145/3486187.3490202

Feeding a Gazetteer: Leveraging word embeddings for toponym mining

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this