@inproceedings{elfardy-etal-2017-bingo,
title = "Bingo at {IJCNLP}-2017 Task 4: Augmenting Data using Machine Translation for Cross-linguistic Customer Feedback Classification",
author = "Elfardy, Heba and
Srivastava, Manisha and
Xiao, Wei and
Kramer, Jared and
Agarwal, Tarun",
editor = "Liu, Chao-Hong and
Nakov, Preslav and
Xue, Nianwen",
booktitle = "Proceedings of the {IJCNLP} 2017, Shared Tasks",
month = dec,
year = "2017",
address = "Taipei, Taiwan",
publisher = "Asian Federation of Natural Language Processing",
url = "https://aclanthology.org/I17-4009",
pages = "59--66",
abstract = "The ability to automatically and accurately process customer feedback is a necessity in the private sector. Unfortunately, customer feedback can be one of the most difficult types of data to work with due to the sheer volume and variety of services, products, languages, and cultures that comprise the customer experience. In order to address this issue, our team built a suite of classifiers trained on a four-language, multi-label corpus released as part of the shared task on {``}Customer Feedback Analysis{''} at IJCNLP 2017. In addition to standard text preprocessing, we translated each dataset into each other language to increase the size of the training datasets. Additionally, we also used word embeddings in our feature engineering step. Ultimately, we trained classifiers using Logistic Regression, Random Forest, and Long Short-Term Memory (LSTM) Recurrent Neural Networks. Overall, we achieved a Macro-Average F-score between 48.7{\%} and 56.0{\%} for the four languages and ranked 3/12 for English, 3/7 for Spanish, 1/8 for French, and 2/7 for Japanese.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elfardy-etal-2017-bingo">
<titleInfo>
<title>Bingo at IJCNLP-2017 Task 4: Augmenting Data using Machine Translation for Cross-linguistic Customer Feedback Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heba</namePart>
<namePart type="family">Elfardy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manisha</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jared</namePart>
<namePart type="family">Kramer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tarun</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the IJCNLP 2017, Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asian Federation of Natural Language Processing</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The ability to automatically and accurately process customer feedback is a necessity in the private sector. Unfortunately, customer feedback can be one of the most difficult types of data to work with due to the sheer volume and variety of services, products, languages, and cultures that comprise the customer experience. In order to address this issue, our team built a suite of classifiers trained on a four-language, multi-label corpus released as part of the shared task on “Customer Feedback Analysis” at IJCNLP 2017. In addition to standard text preprocessing, we translated each dataset into each other language to increase the size of the training datasets. Additionally, we also used word embeddings in our feature engineering step. Ultimately, we trained classifiers using Logistic Regression, Random Forest, and Long Short-Term Memory (LSTM) Recurrent Neural Networks. Overall, we achieved a Macro-Average F-score between 48.7% and 56.0% for the four languages and ranked 3/12 for English, 3/7 for Spanish, 1/8 for French, and 2/7 for Japanese.</abstract>
<identifier type="citekey">elfardy-etal-2017-bingo</identifier>
<location>
<url>https://aclanthology.org/I17-4009</url>
</location>
<part>
<date>2017-12</date>
<extent unit="page">
<start>59</start>
<end>66</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bingo at IJCNLP-2017 Task 4: Augmenting Data using Machine Translation for Cross-linguistic Customer Feedback Classification
%A Elfardy, Heba
%A Srivastava, Manisha
%A Xiao, Wei
%A Kramer, Jared
%A Agarwal, Tarun
%Y Liu, Chao-Hong
%Y Nakov, Preslav
%Y Xue, Nianwen
%S Proceedings of the IJCNLP 2017, Shared Tasks
%D 2017
%8 December
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F elfardy-etal-2017-bingo
%X The ability to automatically and accurately process customer feedback is a necessity in the private sector. Unfortunately, customer feedback can be one of the most difficult types of data to work with due to the sheer volume and variety of services, products, languages, and cultures that comprise the customer experience. In order to address this issue, our team built a suite of classifiers trained on a four-language, multi-label corpus released as part of the shared task on “Customer Feedback Analysis” at IJCNLP 2017. In addition to standard text preprocessing, we translated each dataset into each other language to increase the size of the training datasets. Additionally, we also used word embeddings in our feature engineering step. Ultimately, we trained classifiers using Logistic Regression, Random Forest, and Long Short-Term Memory (LSTM) Recurrent Neural Networks. Overall, we achieved a Macro-Average F-score between 48.7% and 56.0% for the four languages and ranked 3/12 for English, 3/7 for Spanish, 1/8 for French, and 2/7 for Japanese.
%U https://aclanthology.org/I17-4009
%P 59-66
Markdown (Informal)
[Bingo at IJCNLP-2017 Task 4: Augmenting Data using Machine Translation for Cross-linguistic Customer Feedback Classification](https://aclanthology.org/I17-4009) (Elfardy et al., IJCNLP 2017)
ACL