Cargando…

A pragmatic guide to geoparsing evaluation: Toponyms, Named Entity Recognition and pragmatics

Empirical methods in geoparsing have thus far lacked a standard evaluation framework describing the task, metrics and data used to compare state-of-the-art systems. Evaluation is further made inconsistent, even unrepresentative of real world usage by the lack of distinction between the different typ...

Descripción completa

Detalles Bibliográficos
Autores principales: Gritta, Milan, Pilehvar, Mohammad Taher, Collier, Nigel
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Netherlands 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7406539/
https://www.ncbi.nlm.nih.gov/pubmed/32802011
http://dx.doi.org/10.1007/s10579-019-09475-3
_version_ 1783567445239267328
author Gritta, Milan
Pilehvar, Mohammad Taher
Collier, Nigel
author_facet Gritta, Milan
Pilehvar, Mohammad Taher
Collier, Nigel
author_sort Gritta, Milan
collection PubMed
description Empirical methods in geoparsing have thus far lacked a standard evaluation framework describing the task, metrics and data used to compare state-of-the-art systems. Evaluation is further made inconsistent, even unrepresentative of real world usage by the lack of distinction between the different types of toponyms, which necessitates new guidelines, a consolidation of metrics and a detailed toponym taxonomy with implications for Named Entity Recognition (NER) and beyond. To address these deficiencies, our manuscript introduces a new framework in three parts. (Part 1) Task Definition: clarified via corpus linguistic analysis proposing a fine-grained Pragmatic Taxonomy of Toponyms. (Part 2) Metrics: discussed and reviewed for a rigorous evaluation including recommendations for NER/Geoparsing practitioners. (Part 3) Evaluation data: shared via a new dataset called GeoWebNews to provide test/train examples and enable immediate use of our contributions. In addition to fine-grained Geotagging and Toponym Resolution (Geocoding), this dataset is also suitable for prototyping and evaluating machine learning NLP models.
format Online
Article
Text
id pubmed-7406539
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Springer Netherlands
record_format MEDLINE/PubMed
spelling pubmed-74065392020-08-13 A pragmatic guide to geoparsing evaluation: Toponyms, Named Entity Recognition and pragmatics Gritta, Milan Pilehvar, Mohammad Taher Collier, Nigel Lang Resour Eval Original Paper Empirical methods in geoparsing have thus far lacked a standard evaluation framework describing the task, metrics and data used to compare state-of-the-art systems. Evaluation is further made inconsistent, even unrepresentative of real world usage by the lack of distinction between the different types of toponyms, which necessitates new guidelines, a consolidation of metrics and a detailed toponym taxonomy with implications for Named Entity Recognition (NER) and beyond. To address these deficiencies, our manuscript introduces a new framework in three parts. (Part 1) Task Definition: clarified via corpus linguistic analysis proposing a fine-grained Pragmatic Taxonomy of Toponyms. (Part 2) Metrics: discussed and reviewed for a rigorous evaluation including recommendations for NER/Geoparsing practitioners. (Part 3) Evaluation data: shared via a new dataset called GeoWebNews to provide test/train examples and enable immediate use of our contributions. In addition to fine-grained Geotagging and Toponym Resolution (Geocoding), this dataset is also suitable for prototyping and evaluating machine learning NLP models. Springer Netherlands 2019-09-19 2020 /pmc/articles/PMC7406539/ /pubmed/32802011 http://dx.doi.org/10.1007/s10579-019-09475-3 Text en © The Author(s) 2019 Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
spellingShingle Original Paper
Gritta, Milan
Pilehvar, Mohammad Taher
Collier, Nigel
A pragmatic guide to geoparsing evaluation: Toponyms, Named Entity Recognition and pragmatics
title A pragmatic guide to geoparsing evaluation: Toponyms, Named Entity Recognition and pragmatics
title_full A pragmatic guide to geoparsing evaluation: Toponyms, Named Entity Recognition and pragmatics
title_fullStr A pragmatic guide to geoparsing evaluation: Toponyms, Named Entity Recognition and pragmatics
title_full_unstemmed A pragmatic guide to geoparsing evaluation: Toponyms, Named Entity Recognition and pragmatics
title_short A pragmatic guide to geoparsing evaluation: Toponyms, Named Entity Recognition and pragmatics
title_sort pragmatic guide to geoparsing evaluation: toponyms, named entity recognition and pragmatics
topic Original Paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7406539/
https://www.ncbi.nlm.nih.gov/pubmed/32802011
http://dx.doi.org/10.1007/s10579-019-09475-3
work_keys_str_mv AT grittamilan apragmaticguidetogeoparsingevaluationtoponymsnamedentityrecognitionandpragmatics
AT pilehvarmohammadtaher apragmaticguidetogeoparsingevaluationtoponymsnamedentityrecognitionandpragmatics
AT colliernigel apragmaticguidetogeoparsingevaluationtoponymsnamedentityrecognitionandpragmatics
AT grittamilan pragmaticguidetogeoparsingevaluationtoponymsnamedentityrecognitionandpragmatics
AT pilehvarmohammadtaher pragmaticguidetogeoparsingevaluationtoponymsnamedentityrecognitionandpragmatics
AT colliernigel pragmaticguidetogeoparsingevaluationtoponymsnamedentityrecognitionandpragmatics