@inproceedings{wieting-etal-2022-paraphrastic,
title = "Paraphrastic Representations at Scale",
author = "Wieting, John and
Gimpel, Kevin and
Neubig, Graham and
Berg-kirkpatrick, Taylor",
editor = "Che, Wanxiang and
Shutova, Ekaterina",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-demos.38",
doi = "10.18653/v1/2022.emnlp-demos.38",
pages = "379--388",
abstract = "We present a system that allows users to train their own state-of-the-art paraphrastic sentence representations in a variety of languages. We release trained models for English, Arabic, German, Spanish, French, Russian, Turkish, and Chinese. We train these models on large amounts of data, achieving significantly improved performance from our original papers on a suite of monolingual semantic similarity, cross-lingual semantic similarity, and bitext mining tasks. Moreover, the resulting models surpass all prior work on efficient unsupervised semantic textual similarity, even significantly outperforming supervised BERT-based models like Sentence-BERT (Reimers and Gurevych, 2019). Most importantly, our models are orders of magnitude faster than other strong similarity models and can be used on CPU with little difference in inference speed (even improved speed over GPU when using more CPU cores), making these models an attractive choice for users without access to GPUs or for use on embedded devices. Finally, we add significantly increased functionality to the code bases for training paraphrastic sentence models, easing their use for both inference and for training them for any desired language with parallel data. We also include code to automatically download and preprocess training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wieting-etal-2022-paraphrastic">
<titleInfo>
<title>Paraphrastic Representations at Scale</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Wieting</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Gimpel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taylor</namePart>
<namePart type="family">Berg-kirkpatrick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a system that allows users to train their own state-of-the-art paraphrastic sentence representations in a variety of languages. We release trained models for English, Arabic, German, Spanish, French, Russian, Turkish, and Chinese. We train these models on large amounts of data, achieving significantly improved performance from our original papers on a suite of monolingual semantic similarity, cross-lingual semantic similarity, and bitext mining tasks. Moreover, the resulting models surpass all prior work on efficient unsupervised semantic textual similarity, even significantly outperforming supervised BERT-based models like Sentence-BERT (Reimers and Gurevych, 2019). Most importantly, our models are orders of magnitude faster than other strong similarity models and can be used on CPU with little difference in inference speed (even improved speed over GPU when using more CPU cores), making these models an attractive choice for users without access to GPUs or for use on embedded devices. Finally, we add significantly increased functionality to the code bases for training paraphrastic sentence models, easing their use for both inference and for training them for any desired language with parallel data. We also include code to automatically download and preprocess training data.</abstract>
<identifier type="citekey">wieting-etal-2022-paraphrastic</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-demos.38</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-demos.38</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>379</start>
<end>388</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Paraphrastic Representations at Scale
%A Wieting, John
%A Gimpel, Kevin
%A Neubig, Graham
%A Berg-kirkpatrick, Taylor
%Y Che, Wanxiang
%Y Shutova, Ekaterina
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F wieting-etal-2022-paraphrastic
%X We present a system that allows users to train their own state-of-the-art paraphrastic sentence representations in a variety of languages. We release trained models for English, Arabic, German, Spanish, French, Russian, Turkish, and Chinese. We train these models on large amounts of data, achieving significantly improved performance from our original papers on a suite of monolingual semantic similarity, cross-lingual semantic similarity, and bitext mining tasks. Moreover, the resulting models surpass all prior work on efficient unsupervised semantic textual similarity, even significantly outperforming supervised BERT-based models like Sentence-BERT (Reimers and Gurevych, 2019). Most importantly, our models are orders of magnitude faster than other strong similarity models and can be used on CPU with little difference in inference speed (even improved speed over GPU when using more CPU cores), making these models an attractive choice for users without access to GPUs or for use on embedded devices. Finally, we add significantly increased functionality to the code bases for training paraphrastic sentence models, easing their use for both inference and for training them for any desired language with parallel data. We also include code to automatically download and preprocess training data.
%R 10.18653/v1/2022.emnlp-demos.38
%U https://aclanthology.org/2022.emnlp-demos.38
%U https://doi.org/10.18653/v1/2022.emnlp-demos.38
%P 379-388
Markdown (Informal)
[Paraphrastic Representations at Scale](https://aclanthology.org/2022.emnlp-demos.38) (Wieting et al., EMNLP 2022)
ACL
- John Wieting, Kevin Gimpel, Graham Neubig, and Taylor Berg-kirkpatrick. 2022. Paraphrastic Representations at Scale. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 379–388, Abu Dhabi, UAE. Association for Computational Linguistics.