@inproceedings{gupta-gupta-2021-unsupervised,
title = "Unsupervised Contextualized Document Representation",
author = "Gupta, Ankur and
Gupta, Vivek",
booktitle = "Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing",
month = nov,
year = "2021",
address = "Virtual",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sustainlp-1.17",
doi = "10.18653/v1/2021.sustainlp-1.17",
pages = "166--173",
abstract = "Several NLP tasks need the effective repre-sentation of text documents.Arora et al.,2017 demonstrate that simple weighted aver-aging of word vectors frequently outperformsneural models. SCDV (Mekala et al., 2017)further extends this from sentences to docu-ments by employing soft and sparse cluster-ing over pre-computed word vectors. How-ever, both techniques ignore the polysemyand contextual character of words.In thispaper, we address this issue by proposingSCDV+BERT(ctxd), a simple and effective un-supervised representation that combines con-textualized BERT (Devlin et al., 2019) basedword embedding for word sense disambigua-tion with SCDV soft clustering approach. Weshow that our embeddings outperform origi-nal SCDV, pre-train BERT, and several otherbaselines on many classification datasets. Wealso demonstrate our embeddings effective-ness on other tasks, such as concept match-ing and sentence similarity.In addition,we show that SCDV+BERT(ctxd) outperformsfine-tune BERT and different embedding ap-proaches in scenarios with limited data andonly few shots examples.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-gupta-2021-unsupervised">
<titleInfo>
<title>Unsupervised Contextualized Document Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankur</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Several NLP tasks need the effective repre-sentation of text documents.Arora et al.,2017 demonstrate that simple weighted aver-aging of word vectors frequently outperformsneural models. SCDV (Mekala et al., 2017)further extends this from sentences to docu-ments by employing soft and sparse cluster-ing over pre-computed word vectors. How-ever, both techniques ignore the polysemyand contextual character of words.In thispaper, we address this issue by proposingSCDV+BERT(ctxd), a simple and effective un-supervised representation that combines con-textualized BERT (Devlin et al., 2019) basedword embedding for word sense disambigua-tion with SCDV soft clustering approach. Weshow that our embeddings outperform origi-nal SCDV, pre-train BERT, and several otherbaselines on many classification datasets. Wealso demonstrate our embeddings effective-ness on other tasks, such as concept match-ing and sentence similarity.In addition,we show that SCDV+BERT(ctxd) outperformsfine-tune BERT and different embedding ap-proaches in scenarios with limited data andonly few shots examples.</abstract>
<identifier type="citekey">gupta-gupta-2021-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2021.sustainlp-1.17</identifier>
<location>
<url>https://aclanthology.org/2021.sustainlp-1.17</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>166</start>
<end>173</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Contextualized Document Representation
%A Gupta, Ankur
%A Gupta, Vivek
%S Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Virtual
%F gupta-gupta-2021-unsupervised
%X Several NLP tasks need the effective repre-sentation of text documents.Arora et al.,2017 demonstrate that simple weighted aver-aging of word vectors frequently outperformsneural models. SCDV (Mekala et al., 2017)further extends this from sentences to docu-ments by employing soft and sparse cluster-ing over pre-computed word vectors. How-ever, both techniques ignore the polysemyand contextual character of words.In thispaper, we address this issue by proposingSCDV+BERT(ctxd), a simple and effective un-supervised representation that combines con-textualized BERT (Devlin et al., 2019) basedword embedding for word sense disambigua-tion with SCDV soft clustering approach. Weshow that our embeddings outperform origi-nal SCDV, pre-train BERT, and several otherbaselines on many classification datasets. Wealso demonstrate our embeddings effective-ness on other tasks, such as concept match-ing and sentence similarity.In addition,we show that SCDV+BERT(ctxd) outperformsfine-tune BERT and different embedding ap-proaches in scenarios with limited data andonly few shots examples.
%R 10.18653/v1/2021.sustainlp-1.17
%U https://aclanthology.org/2021.sustainlp-1.17
%U https://doi.org/10.18653/v1/2021.sustainlp-1.17
%P 166-173
Markdown (Informal)
[Unsupervised Contextualized Document Representation](https://aclanthology.org/2021.sustainlp-1.17) (Gupta & Gupta, sustainlp 2021)
ACL