@inproceedings{meisheri-khadilkar-2018-learning,
title = "Learning representations for sentiment classification using Multi-task framework",
author = "Meisheri, Hardik and
Khadilkar, Harshad",
editor = "Balahur, Alexandra and
Mohammad, Saif M. and
Hoste, Veronique and
Klinger, Roman",
booktitle = "Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6244",
doi = "10.18653/v1/W18-6244",
pages = "299--308",
abstract = "Most of the existing state of the art sentiment classification techniques involve the use of pre-trained embeddings. This paper postulates a generalized representation that collates training on multiple datasets using a Multi-task learning framework. We incorporate publicly available, pre-trained embeddings with Bidirectional LSTM{'}s to develop the multi-task model. We validate the representations on an independent test Irony dataset that can contain several sentiments within each sample, with an arbitrary distribution. Our experiments show a significant improvement in results as compared to the available baselines for individual datasets on which independent models are trained. Results also suggest superior performance of the representations generated over Irony dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meisheri-khadilkar-2018-learning">
<titleInfo>
<title>Learning representations for sentiment classification using Multi-task framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hardik</namePart>
<namePart type="family">Meisheri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harshad</namePart>
<namePart type="family">Khadilkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Balahur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</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>Most of the existing state of the art sentiment classification techniques involve the use of pre-trained embeddings. This paper postulates a generalized representation that collates training on multiple datasets using a Multi-task learning framework. We incorporate publicly available, pre-trained embeddings with Bidirectional LSTM’s to develop the multi-task model. We validate the representations on an independent test Irony dataset that can contain several sentiments within each sample, with an arbitrary distribution. Our experiments show a significant improvement in results as compared to the available baselines for individual datasets on which independent models are trained. Results also suggest superior performance of the representations generated over Irony dataset.</abstract>
<identifier type="citekey">meisheri-khadilkar-2018-learning</identifier>
<identifier type="doi">10.18653/v1/W18-6244</identifier>
<location>
<url>https://aclanthology.org/W18-6244</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>299</start>
<end>308</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning representations for sentiment classification using Multi-task framework
%A Meisheri, Hardik
%A Khadilkar, Harshad
%Y Balahur, Alexandra
%Y Mohammad, Saif M.
%Y Hoste, Veronique
%Y Klinger, Roman
%S Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F meisheri-khadilkar-2018-learning
%X Most of the existing state of the art sentiment classification techniques involve the use of pre-trained embeddings. This paper postulates a generalized representation that collates training on multiple datasets using a Multi-task learning framework. We incorporate publicly available, pre-trained embeddings with Bidirectional LSTM’s to develop the multi-task model. We validate the representations on an independent test Irony dataset that can contain several sentiments within each sample, with an arbitrary distribution. Our experiments show a significant improvement in results as compared to the available baselines for individual datasets on which independent models are trained. Results also suggest superior performance of the representations generated over Irony dataset.
%R 10.18653/v1/W18-6244
%U https://aclanthology.org/W18-6244
%U https://doi.org/10.18653/v1/W18-6244
%P 299-308
Markdown (Informal)
[Learning representations for sentiment classification using Multi-task framework](https://aclanthology.org/W18-6244) (Meisheri & Khadilkar, WASSA 2018)
ACL