@inproceedings{miyazaki-etal-2018-twitter,
title = "{T}witter Geolocation using Knowledge-Based Methods",
author = "Miyazaki, Taro and
Rahimi, Afshin and
Cohn, Trevor and
Baldwin, Timothy",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the 2018 {EMNLP} Workshop W-{NUT}: The 4th Workshop on Noisy User-generated Text",
month = nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6102/",
doi = "10.18653/v1/W18-6102",
pages = "7--16",
abstract = "Automatic geolocation of microblog posts from their text content is particularly difficult because many location-indicative terms are rare terms, notably entity names such as locations, people or local organisations. Their low frequency means that key terms observed in testing are often unseen in training, such that standard classifiers are unable to learn weights for them. We propose a method for reasoning over such terms using a knowledge base, through exploiting their relations with other entities. Our technique uses a graph embedding over the knowledge base, which we couple with a text representation to learn a geolocation classifier, trained end-to-end. We show that our method improves over purely text-based methods, which we ascribe to more robust treatment of low-count and out-of-vocabulary entities."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miyazaki-etal-2018-twitter">
<titleInfo>
<title>Twitter Geolocation using Knowledge-Based Methods</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Miyazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text</title>
</titleInfo>
<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">Alan</namePart>
<namePart type="family">Ritter</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>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic geolocation of microblog posts from their text content is particularly difficult because many location-indicative terms are rare terms, notably entity names such as locations, people or local organisations. Their low frequency means that key terms observed in testing are often unseen in training, such that standard classifiers are unable to learn weights for them. We propose a method for reasoning over such terms using a knowledge base, through exploiting their relations with other entities. Our technique uses a graph embedding over the knowledge base, which we couple with a text representation to learn a geolocation classifier, trained end-to-end. We show that our method improves over purely text-based methods, which we ascribe to more robust treatment of low-count and out-of-vocabulary entities.</abstract>
<identifier type="citekey">miyazaki-etal-2018-twitter</identifier>
<identifier type="doi">10.18653/v1/W18-6102</identifier>
<location>
<url>https://aclanthology.org/W18-6102/</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>7</start>
<end>16</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Twitter Geolocation using Knowledge-Based Methods
%A Miyazaki, Taro
%A Rahimi, Afshin
%A Cohn, Trevor
%A Baldwin, Timothy
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F miyazaki-etal-2018-twitter
%X Automatic geolocation of microblog posts from their text content is particularly difficult because many location-indicative terms are rare terms, notably entity names such as locations, people or local organisations. Their low frequency means that key terms observed in testing are often unseen in training, such that standard classifiers are unable to learn weights for them. We propose a method for reasoning over such terms using a knowledge base, through exploiting their relations with other entities. Our technique uses a graph embedding over the knowledge base, which we couple with a text representation to learn a geolocation classifier, trained end-to-end. We show that our method improves over purely text-based methods, which we ascribe to more robust treatment of low-count and out-of-vocabulary entities.
%R 10.18653/v1/W18-6102
%U https://aclanthology.org/W18-6102/
%U https://doi.org/10.18653/v1/W18-6102
%P 7-16
Markdown (Informal)
[Twitter Geolocation using Knowledge-Based Methods](https://aclanthology.org/W18-6102/) (Miyazaki et al., WNUT 2018)
- Twitter Geolocation using Knowledge-Based Methods (Miyazaki et al., WNUT 2018)
ACL
- Taro Miyazaki, Afshin Rahimi, Trevor Cohn, and Timothy Baldwin. 2018. Twitter Geolocation using Knowledge-Based Methods. In Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text, pages 7–16, Brussels, Belgium. Association for Computational Linguistics.