@inproceedings{verma-etal-2020-sthal,
title = "{STHAL}: Location-mention Identification in Tweets of {I}ndian-context",
author = "Verma, Kartik and
Sinha, Shobhit and
Akhtar, Md. Shad and
Goyal, Vikram",
editor = "Bhattacharyya, Pushpak and
Sharma, Dipti Misra and
Sangal, Rajeev",
booktitle = "Proceedings of the 17th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2020",
address = "Indian Institute of Technology Patna, Patna, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2020.icon-main.52/",
pages = "379--383",
abstract = "We investigate the problem of extracting Indian-locations from a given crowd-sourced textual dataset. The problem of extracting fine-grained Indian-locations has many challenges. One challenge in the task is to collect relevant dataset from the crowd-sourced platforms that contain locations. The second challenge lies in extracting the location entities from the collected data. We provide an in-depth review of the information collection process and our annotation guidelines such that a reliable dataset annotation is guaranteed. We evaluate many recent algorithms and models, including Conditional Random fields (CRF), Bi-LSTM-CNN and BERT (Bidirectional Encoder Representations from Transformers), on our developed dataset named . The study shows the best F1-score of 72.49{\%} for BERT, followed by Bi-LSTM-CNN and CRF. As a result of our work, we prepare a publicly-available annotated dataset of Indian geolocations that can be used by the research community. Code and dataset are available at \url{https://github.com/vkartik2k/STHAL}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="verma-etal-2020-sthal">
<titleInfo>
<title>STHAL: Location-mention Identification in Tweets of Indian-context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kartik</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shobhit</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Shad</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vikram</namePart>
<namePart type="family">Goyal</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 17th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="given">Misra</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajeev</namePart>
<namePart type="family">Sangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Indian Institute of Technology Patna, Patna, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We investigate the problem of extracting Indian-locations from a given crowd-sourced textual dataset. The problem of extracting fine-grained Indian-locations has many challenges. One challenge in the task is to collect relevant dataset from the crowd-sourced platforms that contain locations. The second challenge lies in extracting the location entities from the collected data. We provide an in-depth review of the information collection process and our annotation guidelines such that a reliable dataset annotation is guaranteed. We evaluate many recent algorithms and models, including Conditional Random fields (CRF), Bi-LSTM-CNN and BERT (Bidirectional Encoder Representations from Transformers), on our developed dataset named . The study shows the best F1-score of 72.49% for BERT, followed by Bi-LSTM-CNN and CRF. As a result of our work, we prepare a publicly-available annotated dataset of Indian geolocations that can be used by the research community. Code and dataset are available at https://github.com/vkartik2k/STHAL.</abstract>
<identifier type="citekey">verma-etal-2020-sthal</identifier>
<location>
<url>https://aclanthology.org/2020.icon-main.52/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>379</start>
<end>383</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T STHAL: Location-mention Identification in Tweets of Indian-context
%A Verma, Kartik
%A Sinha, Shobhit
%A Akhtar, Md. Shad
%A Goyal, Vikram
%Y Bhattacharyya, Pushpak
%Y Sharma, Dipti Misra
%Y Sangal, Rajeev
%S Proceedings of the 17th International Conference on Natural Language Processing (ICON)
%D 2020
%8 December
%I NLP Association of India (NLPAI)
%C Indian Institute of Technology Patna, Patna, India
%F verma-etal-2020-sthal
%X We investigate the problem of extracting Indian-locations from a given crowd-sourced textual dataset. The problem of extracting fine-grained Indian-locations has many challenges. One challenge in the task is to collect relevant dataset from the crowd-sourced platforms that contain locations. The second challenge lies in extracting the location entities from the collected data. We provide an in-depth review of the information collection process and our annotation guidelines such that a reliable dataset annotation is guaranteed. We evaluate many recent algorithms and models, including Conditional Random fields (CRF), Bi-LSTM-CNN and BERT (Bidirectional Encoder Representations from Transformers), on our developed dataset named . The study shows the best F1-score of 72.49% for BERT, followed by Bi-LSTM-CNN and CRF. As a result of our work, we prepare a publicly-available annotated dataset of Indian geolocations that can be used by the research community. Code and dataset are available at https://github.com/vkartik2k/STHAL.
%U https://aclanthology.org/2020.icon-main.52/
%P 379-383
Markdown (Informal)
[STHAL: Location-mention Identification in Tweets of Indian-context](https://aclanthology.org/2020.icon-main.52/) (Verma et al., ICON 2020)
ACL