Fuzzy-Based Language Grounding of Geographical References

From Writers to Readers

Alejandro Ramos, Jose M. Alonso (Corresponding Author), Ehud Reiter, Kees Van Deemter, Albert Gatt

Research output: Contribution to journalArticle

Abstract

We describe an applied methodology to build fuzzy models of geographical expressions, which are meant to be used for natural language generation purposes. Our approach encompasses a language grounding task within the development of an actual data-to-text system for the generation of textual descriptions of live weather data. For this, we gathered data from meteorologists through a survey and built consistent fuzzy models that aggregate the interpersonal variations found among the experts. A subset of the models was utilized in an illustrative use case, where we generated linguistic descriptions of weather maps for specific geographical expressions. These were used in a task-based evaluation to determine how well eographical expressions grounded on the models.
Original languageEnglish
JournalInternational Journal of Computational Intelligence Systems
Publication statusAccepted/In press - 23 Aug 2019

Fingerprint

Electric grounding
Linguistics

Keywords

  • natural language generation
  • linguistic descriptions of data
  • data-to-text
  • geo-referenced data
  • language grounding
  • fuzzy sets

Cite this

Fuzzy-Based Language Grounding of Geographical References : From Writers to Readers. / Ramos, Alejandro ; Alonso, Jose M. (Corresponding Author); Reiter, Ehud; Van Deemter, Kees; Gatt, Albert.

In: International Journal of Computational Intelligence Systems, 23.08.2019.

Research output: Contribution to journalArticle

@article{8ac3a26999b345faa11c50b990c74168,
title = "Fuzzy-Based Language Grounding of Geographical References: From Writers to Readers",
abstract = "We describe an applied methodology to build fuzzy models of geographical expressions, which are meant to be used for natural language generation purposes. Our approach encompasses a language grounding task within the development of an actual data-to-text system for the generation of textual descriptions of live weather data. For this, we gathered data from meteorologists through a survey and built consistent fuzzy models that aggregate the interpersonal variations found among the experts. A subset of the models was utilized in an illustrative use case, where we generated linguistic descriptions of weather maps for specific geographical expressions. These were used in a task-based evaluation to determine how well eographical expressions grounded on the models.",
keywords = "natural language generation, linguistic descriptions of data, data-to-text, geo-referenced data, language grounding, fuzzy sets",
author = "Alejandro Ramos and Alonso, {Jose M.} and Ehud Reiter and {Van Deemter}, Kees and Albert Gatt",
note = "Jose M. Alonso is Ramon y Cajal Researcher (RYC-2016-19802). This research was also funded by the Spanish Ministry of Science, Innovation and Universities (grants RTI2018-099646-BI00, TIN2017-84796-C2-1-R and TIN2017-90773-REDT) and the Galician Ministry of Education, University and Professional Training (grants ED431F2018/02, ED431C 2018/29 and “accreditation 2016-2019, ED431G/08”). All grants were co-funded by the European Regional Development Fund (ERDF/FEDER program).",
year = "2019",
month = "8",
day = "23",
language = "English",
journal = "International Journal of Computational Intelligence Systems",
issn = "1875-6891",

}

TY - JOUR

T1 - Fuzzy-Based Language Grounding of Geographical References

T2 - From Writers to Readers

AU - Ramos, Alejandro

AU - Alonso, Jose M.

AU - Reiter, Ehud

AU - Van Deemter, Kees

AU - Gatt, Albert

N1 - Jose M. Alonso is Ramon y Cajal Researcher (RYC-2016-19802). This research was also funded by the Spanish Ministry of Science, Innovation and Universities (grants RTI2018-099646-BI00, TIN2017-84796-C2-1-R and TIN2017-90773-REDT) and the Galician Ministry of Education, University and Professional Training (grants ED431F2018/02, ED431C 2018/29 and “accreditation 2016-2019, ED431G/08”). All grants were co-funded by the European Regional Development Fund (ERDF/FEDER program).

PY - 2019/8/23

Y1 - 2019/8/23

N2 - We describe an applied methodology to build fuzzy models of geographical expressions, which are meant to be used for natural language generation purposes. Our approach encompasses a language grounding task within the development of an actual data-to-text system for the generation of textual descriptions of live weather data. For this, we gathered data from meteorologists through a survey and built consistent fuzzy models that aggregate the interpersonal variations found among the experts. A subset of the models was utilized in an illustrative use case, where we generated linguistic descriptions of weather maps for specific geographical expressions. These were used in a task-based evaluation to determine how well eographical expressions grounded on the models.

AB - We describe an applied methodology to build fuzzy models of geographical expressions, which are meant to be used for natural language generation purposes. Our approach encompasses a language grounding task within the development of an actual data-to-text system for the generation of textual descriptions of live weather data. For this, we gathered data from meteorologists through a survey and built consistent fuzzy models that aggregate the interpersonal variations found among the experts. A subset of the models was utilized in an illustrative use case, where we generated linguistic descriptions of weather maps for specific geographical expressions. These were used in a task-based evaluation to determine how well eographical expressions grounded on the models.

KW - natural language generation

KW - linguistic descriptions of data

KW - data-to-text

KW - geo-referenced data

KW - language grounding

KW - fuzzy sets

M3 - Article

JO - International Journal of Computational Intelligence Systems

JF - International Journal of Computational Intelligence Systems

SN - 1875-6891

ER -