@inproceedings{mukadam-etal-2020-representation,
title = "A Representation Learning Approach to Animal Biodiversity Conservation",
author = "Mukadam, Meet and
Jayaram, Mandhara and
Zhang, Yongfeng",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.26/",
doi = "10.18653/v1/2020.coling-main.26",
pages = "294--305",
abstract = "Generating knowledge from natural language data has aided in solving many artificial intelligence problems. Vector representations of words have been the driving force behind the majority of natural language processing tasks. This paper develops a novel approach for predicting the conservation status of animal species using custom generated scientific name embeddings. We use two different vector embeddings generated using representation learning on Wikipedia text and animal taxonomy data. We generate name embeddings for all species in the animal kingdom using unsupervised learning and build a model on the IUCN Red List dataset to classify species into endangered or least-concern. To our knowledge, this is the first work that makes use of learnt features instead of handcrafted features for this task and achieves competitive results. Based on the high confidence results of our model, we also predict the conservation status of data deficient species whose conservation status is still unknown and thus steering more focus towards them for protection. These embeddings have also been made publicly available here. We believe this will greatly help in solving various downstream tasks and further advance research in the cross-domain involving natural language processing, conservation biology, and life sciences."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mukadam-etal-2020-representation">
<titleInfo>
<title>A Representation Learning Approach to Animal Biodiversity Conservation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meet</namePart>
<namePart type="family">Mukadam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mandhara</namePart>
<namePart type="family">Jayaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongfeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generating knowledge from natural language data has aided in solving many artificial intelligence problems. Vector representations of words have been the driving force behind the majority of natural language processing tasks. This paper develops a novel approach for predicting the conservation status of animal species using custom generated scientific name embeddings. We use two different vector embeddings generated using representation learning on Wikipedia text and animal taxonomy data. We generate name embeddings for all species in the animal kingdom using unsupervised learning and build a model on the IUCN Red List dataset to classify species into endangered or least-concern. To our knowledge, this is the first work that makes use of learnt features instead of handcrafted features for this task and achieves competitive results. Based on the high confidence results of our model, we also predict the conservation status of data deficient species whose conservation status is still unknown and thus steering more focus towards them for protection. These embeddings have also been made publicly available here. We believe this will greatly help in solving various downstream tasks and further advance research in the cross-domain involving natural language processing, conservation biology, and life sciences.</abstract>
<identifier type="citekey">mukadam-etal-2020-representation</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.26</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.26/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>294</start>
<end>305</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Representation Learning Approach to Animal Biodiversity Conservation
%A Mukadam, Meet
%A Jayaram, Mandhara
%A Zhang, Yongfeng
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F mukadam-etal-2020-representation
%X Generating knowledge from natural language data has aided in solving many artificial intelligence problems. Vector representations of words have been the driving force behind the majority of natural language processing tasks. This paper develops a novel approach for predicting the conservation status of animal species using custom generated scientific name embeddings. We use two different vector embeddings generated using representation learning on Wikipedia text and animal taxonomy data. We generate name embeddings for all species in the animal kingdom using unsupervised learning and build a model on the IUCN Red List dataset to classify species into endangered or least-concern. To our knowledge, this is the first work that makes use of learnt features instead of handcrafted features for this task and achieves competitive results. Based on the high confidence results of our model, we also predict the conservation status of data deficient species whose conservation status is still unknown and thus steering more focus towards them for protection. These embeddings have also been made publicly available here. We believe this will greatly help in solving various downstream tasks and further advance research in the cross-domain involving natural language processing, conservation biology, and life sciences.
%R 10.18653/v1/2020.coling-main.26
%U https://aclanthology.org/2020.coling-main.26/
%U https://doi.org/10.18653/v1/2020.coling-main.26
%P 294-305
Markdown (Informal)
[A Representation Learning Approach to Animal Biodiversity Conservation](https://aclanthology.org/2020.coling-main.26/) (Mukadam et al., COLING 2020)
ACL