@inproceedings{dhyani-2017-ohiostate,
title = "{O}hio{S}tate at {IJCNLP}-2017 Task 4: Exploring Neural Architectures for Multilingual Customer Feedback Analysis",
author = "Dhyani, Dushyanta",
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/I17-4028",
pages = "170--173",
abstract = "This paper describes our systems for IJCNLP 2017 Shared Task on Customer Feedback Analysis. We experimented with simple neural architectures that gave competitive performance on certain tasks. This includes shallow CNN and Bi-Directional LSTM architectures with Facebook{'}s Fasttext as a baseline model. Our best performing model was in the Top 5 systems using the Exact-Accuracy and Micro-Average-F1 metrics for the Spanish (85.28{\%} for both) and French (70{\%} and 73.17{\%} respectively) task, and outperformed all the other models on comment (87.28{\%}) and meaningless (51.85{\%}) tags using Micro Average F1 by Tags metric for the French task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dhyani-2017-ohiostate">
<titleInfo>
<title>OhioState at IJCNLP-2017 Task 4: Exploring Neural Architectures for Multilingual Customer Feedback Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dushyanta</namePart>
<namePart type="family">Dhyani</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>This paper describes our systems for IJCNLP 2017 Shared Task on Customer Feedback Analysis. We experimented with simple neural architectures that gave competitive performance on certain tasks. This includes shallow CNN and Bi-Directional LSTM architectures with Facebook’s Fasttext as a baseline model. Our best performing model was in the Top 5 systems using the Exact-Accuracy and Micro-Average-F1 metrics for the Spanish (85.28% for both) and French (70% and 73.17% respectively) task, and outperformed all the other models on comment (87.28%) and meaningless (51.85%) tags using Micro Average F1 by Tags metric for the French task.</abstract>
<identifier type="citekey">dhyani-2017-ohiostate</identifier>
<location>
<url>https://aclanthology.org/I17-4028</url>
</location>
<part>
<date>2017-12</date>
<extent unit="page">
<start>170</start>
<end>173</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OhioState at IJCNLP-2017 Task 4: Exploring Neural Architectures for Multilingual Customer Feedback Analysis
%A Dhyani, Dushyanta
%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 dhyani-2017-ohiostate
%X This paper describes our systems for IJCNLP 2017 Shared Task on Customer Feedback Analysis. We experimented with simple neural architectures that gave competitive performance on certain tasks. This includes shallow CNN and Bi-Directional LSTM architectures with Facebook’s Fasttext as a baseline model. Our best performing model was in the Top 5 systems using the Exact-Accuracy and Micro-Average-F1 metrics for the Spanish (85.28% for both) and French (70% and 73.17% respectively) task, and outperformed all the other models on comment (87.28%) and meaningless (51.85%) tags using Micro Average F1 by Tags metric for the French task.
%U https://aclanthology.org/I17-4028
%P 170-173
Markdown (Informal)
[OhioState at IJCNLP-2017 Task 4: Exploring Neural Architectures for Multilingual Customer Feedback Analysis](https://aclanthology.org/I17-4028) (Dhyani, IJCNLP 2017)
ACL