@inproceedings{jayasinghe-etal-2016-csiro,
title = "{CSIRO} {D}ata61 at the {WNUT} Geo Shared Task",
author = "Jayasinghe, Gaya and
Jin, Brian and
Mchugh, James and
Robinson, Bella and
Wan, Stephen",
editor = "Han, Bo and
Ritter, Alan and
Derczynski, Leon and
Xu, Wei and
Baldwin, Tim",
booktitle = "Proceedings of the 2nd Workshop on Noisy User-generated Text ({WNUT})",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-3929",
pages = "218--226",
abstract = "In this paper, we describe CSIRO Data61{'}s participation in the Geolocation shared task at the Workshop for Noisy User-generated Text. Our approach was to use ensemble methods to capitalise on four component methods: heuristics based on metadata, a label propagation method, timezone text classifiers, and an information retrieval approach. The ensembles we explored focused on examining the role of language technologies in geolocation prediction and also in examining the use of hard voting and cascading ensemble methods. Based on the accuracy of city-level predictions, our systems were the best performing submissions at this year{'}s shared task. Furthermore, when estimating the latitude and longitude of a user, our median error distance was accurate to within 30 kilometers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jayasinghe-etal-2016-csiro">
<titleInfo>
<title>CSIRO Data61 at the WNUT Geo Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gaya</namePart>
<namePart type="family">Jayasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Mchugh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bella</namePart>
<namePart type="family">Robinson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe CSIRO Data61’s participation in the Geolocation shared task at the Workshop for Noisy User-generated Text. Our approach was to use ensemble methods to capitalise on four component methods: heuristics based on metadata, a label propagation method, timezone text classifiers, and an information retrieval approach. The ensembles we explored focused on examining the role of language technologies in geolocation prediction and also in examining the use of hard voting and cascading ensemble methods. Based on the accuracy of city-level predictions, our systems were the best performing submissions at this year’s shared task. Furthermore, when estimating the latitude and longitude of a user, our median error distance was accurate to within 30 kilometers.</abstract>
<identifier type="citekey">jayasinghe-etal-2016-csiro</identifier>
<location>
<url>https://aclanthology.org/W16-3929</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>218</start>
<end>226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CSIRO Data61 at the WNUT Geo Shared Task
%A Jayasinghe, Gaya
%A Jin, Brian
%A Mchugh, James
%A Robinson, Bella
%A Wan, Stephen
%Y Han, Bo
%Y Ritter, Alan
%Y Derczynski, Leon
%Y Xu, Wei
%Y Baldwin, Tim
%S Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F jayasinghe-etal-2016-csiro
%X In this paper, we describe CSIRO Data61’s participation in the Geolocation shared task at the Workshop for Noisy User-generated Text. Our approach was to use ensemble methods to capitalise on four component methods: heuristics based on metadata, a label propagation method, timezone text classifiers, and an information retrieval approach. The ensembles we explored focused on examining the role of language technologies in geolocation prediction and also in examining the use of hard voting and cascading ensemble methods. Based on the accuracy of city-level predictions, our systems were the best performing submissions at this year’s shared task. Furthermore, when estimating the latitude and longitude of a user, our median error distance was accurate to within 30 kilometers.
%U https://aclanthology.org/W16-3929
%P 218-226
Markdown (Informal)
[CSIRO Data61 at the WNUT Geo Shared Task](https://aclanthology.org/W16-3929) (Jayasinghe et al., WNUT 2016)
ACL
- Gaya Jayasinghe, Brian Jin, James Mchugh, Bella Robinson, and Stephen Wan. 2016. CSIRO Data61 at the WNUT Geo Shared Task. In Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT), pages 218–226, Osaka, Japan. The COLING 2016 Organizing Committee.