@inproceedings{ella-etal-2026-disambiguating,
title = "Disambiguating Geographic Names in Biodiversity Occurrence Data: A Retrieval-Augmented Generation Approach",
author = "Ella, Yanni Jose C. and
Laviste, Monica Ashley R. and
Lastimoso, John Michael L. and
Santia{\~n}ez, Wilfred John E. and
Batista-Navarro, Riza and
Gabud, Roselyn Santos",
editor = "Grasso, Francesca and
Basile, Valerio and
Bosco, Cristina and
Ibrohim, Muhammad Okky and
Skeppstedt, Maria and
Stede, Manfred",
booktitle = "Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2026.nlp4ecology-1.4/",
doi = "10.63317/3m7qkiiy984w",
pages = "42--52",
abstract = "The availability of georeferenced coordinates is essential for biodiversity research, as it enables species distribution modeling and supports conservation planning. However, datasets often contain ambiguous or inconsistent geographic names that reduce spatial accuracy and underscore the need for methods that resolve geographic name ambiguity. While traditional named entity linking strategies are well established, they remain limited in low-resource domains, e.g., in biodiversity contexts, due to the scarcity of annotated training data and high lexical ambiguity of local geographic names. This study proposes a Retrieval-Augmented Generation (RAG) framework to automatically disambiguate Philippine seaweed-related geographic names in databases and literature. This approach utilizes a custom knowledge base of gazetteers to support large language models (LLMs) in the task of geospatial disambiguation. With a disambiguation accuracy of 87.8{\%} within a 5 km distance error threshold, our evaluation shows that the RAG-enabled pipeline significantly outperforms standard LLM baselines (Accuracy@5km = 0{\%}), demonstrating the need for external knowledge to resolve geospatial ambiguity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ella-etal-2026-disambiguating">
<titleInfo>
<title>Disambiguating Geographic Names in Biodiversity Occurrence Data: A Retrieval-Augmented Generation Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanni</namePart>
<namePart type="given">Jose</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Ella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monica</namePart>
<namePart type="given">Ashley</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Laviste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">Michael</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Lastimoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wilfred</namePart>
<namePart type="given">John</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Santiañez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riza</namePart>
<namePart type="family">Batista-Navarro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roselyn</namePart>
<namePart type="given">Santos</namePart>
<namePart type="family">Gabud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Grasso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Bosco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Okky</namePart>
<namePart type="family">Ibrohim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Skeppstedt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manfred</namePart>
<namePart type="family">Stede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The availability of georeferenced coordinates is essential for biodiversity research, as it enables species distribution modeling and supports conservation planning. However, datasets often contain ambiguous or inconsistent geographic names that reduce spatial accuracy and underscore the need for methods that resolve geographic name ambiguity. While traditional named entity linking strategies are well established, they remain limited in low-resource domains, e.g., in biodiversity contexts, due to the scarcity of annotated training data and high lexical ambiguity of local geographic names. This study proposes a Retrieval-Augmented Generation (RAG) framework to automatically disambiguate Philippine seaweed-related geographic names in databases and literature. This approach utilizes a custom knowledge base of gazetteers to support large language models (LLMs) in the task of geospatial disambiguation. With a disambiguation accuracy of 87.8% within a 5 km distance error threshold, our evaluation shows that the RAG-enabled pipeline significantly outperforms standard LLM baselines (Accuracy@5km = 0%), demonstrating the need for external knowledge to resolve geospatial ambiguity.</abstract>
<identifier type="citekey">ella-etal-2026-disambiguating</identifier>
<identifier type="doi">10.63317/3m7qkiiy984w</identifier>
<location>
<url>https://aclanthology.org/2026.nlp4ecology-1.4/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>42</start>
<end>52</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Disambiguating Geographic Names in Biodiversity Occurrence Data: A Retrieval-Augmented Generation Approach
%A Ella, Yanni Jose C.
%A Laviste, Monica Ashley R.
%A Lastimoso, John Michael L.
%A Santiañez, Wilfred John E.
%A Batista-Navarro, Riza
%A Gabud, Roselyn Santos
%Y Grasso, Francesca
%Y Basile, Valerio
%Y Bosco, Cristina
%Y Ibrohim, Muhammad Okky
%Y Skeppstedt, Maria
%Y Stede, Manfred
%S Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing
%D 2026
%8 May
%I European Language Resources Association
%C Palma de Mallorca, Spain
%F ella-etal-2026-disambiguating
%X The availability of georeferenced coordinates is essential for biodiversity research, as it enables species distribution modeling and supports conservation planning. However, datasets often contain ambiguous or inconsistent geographic names that reduce spatial accuracy and underscore the need for methods that resolve geographic name ambiguity. While traditional named entity linking strategies are well established, they remain limited in low-resource domains, e.g., in biodiversity contexts, due to the scarcity of annotated training data and high lexical ambiguity of local geographic names. This study proposes a Retrieval-Augmented Generation (RAG) framework to automatically disambiguate Philippine seaweed-related geographic names in databases and literature. This approach utilizes a custom knowledge base of gazetteers to support large language models (LLMs) in the task of geospatial disambiguation. With a disambiguation accuracy of 87.8% within a 5 km distance error threshold, our evaluation shows that the RAG-enabled pipeline significantly outperforms standard LLM baselines (Accuracy@5km = 0%), demonstrating the need for external knowledge to resolve geospatial ambiguity.
%R 10.63317/3m7qkiiy984w
%U https://aclanthology.org/2026.nlp4ecology-1.4/
%U https://doi.org/10.63317/3m7qkiiy984w
%P 42-52
Markdown (Informal)
[Disambiguating Geographic Names in Biodiversity Occurrence Data: A Retrieval-Augmented Generation Approach](https://aclanthology.org/2026.nlp4ecology-1.4/) (Ella et al., NLP4Ecology 2026)
ACL
- Yanni Jose C. Ella, Monica Ashley R. Laviste, John Michael L. Lastimoso, Wilfred John E. Santiañez, Riza Batista-Navarro, and Roselyn Santos Gabud. 2026. Disambiguating Geographic Names in Biodiversity Occurrence Data: A Retrieval-Augmented Generation Approach. In Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing, pages 42–52, Palma de Mallorca, Spain. European Language Resources Association.