@inproceedings{almarwani-diab-2021-discrete,
title = "Discrete Cosine Transform as Universal Sentence Encoder",
author = "Almarwani, Nada and
Diab, Mona",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.53",
doi = "10.18653/v1/2021.acl-short.53",
pages = "419--426",
abstract = "Modern sentence encoders are used to generate dense vector representations that capture the underlying linguistic characteristics for a sequence of words, including phrases, sentences, or paragraphs. These kinds of representations are ideal for training a classifier for an end task such as sentiment analysis, question answering and text classification. Different models have been proposed to efficiently generate general purpose sentence representations to be used in pretraining protocols. While averaging is the most commonly used efficient sentence encoder, Discrete Cosine Transform (DCT) was recently proposed as an alternative that captures the underlying syntactic characteristics of a given text without compromising practical efficiency compared to averaging. However, as with most other sentence encoders, the DCT sentence encoder was only evaluated in English. To this end, we utilize DCT encoder to generate universal sentence representation for different languages such as German, French, Spanish and Russian. The experimental results clearly show the superior effectiveness of DCT encoding in which consistent performance improvements are achieved over strong baselines on multiple standardized datasets",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almarwani-diab-2021-discrete">
<titleInfo>
<title>Discrete Cosine Transform as Universal Sentence Encoder</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nada</namePart>
<namePart type="family">Almarwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Modern sentence encoders are used to generate dense vector representations that capture the underlying linguistic characteristics for a sequence of words, including phrases, sentences, or paragraphs. These kinds of representations are ideal for training a classifier for an end task such as sentiment analysis, question answering and text classification. Different models have been proposed to efficiently generate general purpose sentence representations to be used in pretraining protocols. While averaging is the most commonly used efficient sentence encoder, Discrete Cosine Transform (DCT) was recently proposed as an alternative that captures the underlying syntactic characteristics of a given text without compromising practical efficiency compared to averaging. However, as with most other sentence encoders, the DCT sentence encoder was only evaluated in English. To this end, we utilize DCT encoder to generate universal sentence representation for different languages such as German, French, Spanish and Russian. The experimental results clearly show the superior effectiveness of DCT encoding in which consistent performance improvements are achieved over strong baselines on multiple standardized datasets</abstract>
<identifier type="citekey">almarwani-diab-2021-discrete</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.53</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.53</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>419</start>
<end>426</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Discrete Cosine Transform as Universal Sentence Encoder
%A Almarwani, Nada
%A Diab, Mona
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F almarwani-diab-2021-discrete
%X Modern sentence encoders are used to generate dense vector representations that capture the underlying linguistic characteristics for a sequence of words, including phrases, sentences, or paragraphs. These kinds of representations are ideal for training a classifier for an end task such as sentiment analysis, question answering and text classification. Different models have been proposed to efficiently generate general purpose sentence representations to be used in pretraining protocols. While averaging is the most commonly used efficient sentence encoder, Discrete Cosine Transform (DCT) was recently proposed as an alternative that captures the underlying syntactic characteristics of a given text without compromising practical efficiency compared to averaging. However, as with most other sentence encoders, the DCT sentence encoder was only evaluated in English. To this end, we utilize DCT encoder to generate universal sentence representation for different languages such as German, French, Spanish and Russian. The experimental results clearly show the superior effectiveness of DCT encoding in which consistent performance improvements are achieved over strong baselines on multiple standardized datasets
%R 10.18653/v1/2021.acl-short.53
%U https://aclanthology.org/2021.acl-short.53
%U https://doi.org/10.18653/v1/2021.acl-short.53
%P 419-426
Markdown (Informal)
[Discrete Cosine Transform as Universal Sentence Encoder](https://aclanthology.org/2021.acl-short.53) (Almarwani & Diab, ACL-IJCNLP 2021)
ACL
- Nada Almarwani and Mona Diab. 2021. Discrete Cosine Transform as Universal Sentence Encoder. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 419–426, Online. Association for Computational Linguistics.