@inproceedings{cer-etal-2018-universal,
title = "Universal Sentence Encoder for {E}nglish",
author = "Cer, Daniel and
Yang, Yinfei and
Kong, Sheng-yi and
Hua, Nan and
Limtiaco, Nicole and
St. John, Rhomni and
Constant, Noah and
Guajardo-Cespedes, Mario and
Yuan, Steve and
Tar, Chris and
Strope, Brian and
Kurzweil, Ray",
editor = "Blanco, Eduardo and
Lu, Wei",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-2029",
doi = "10.18653/v1/D18-2029",
pages = "169--174",
abstract = "We present easy-to-use TensorFlow Hub sentence embedding models having good task transfer performance. Model variants allow for trade-offs between accuracy and compute resources. We report the relationship between model complexity, resources, and transfer performance. Comparisons are made with baselines without transfer learning and to baselines that incorporate word-level transfer. Transfer learning using sentence-level embeddings is shown to outperform models without transfer learning and often those that use only word-level transfer. We show good transfer task performance with minimal training data and obtain encouraging results on word embedding association tests (WEAT) of model bias.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cer-etal-2018-universal">
<titleInfo>
<title>Universal Sentence Encoder for English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Cer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinfei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng-yi</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Hua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicole</namePart>
<namePart type="family">Limtiaco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rhomni</namePart>
<namePart type="family">St. John</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="family">Constant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Guajardo-Cespedes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steve</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Tar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Strope</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ray</namePart>
<namePart type="family">Kurzweil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eduardo</namePart>
<namePart type="family">Blanco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Lu</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>We present easy-to-use TensorFlow Hub sentence embedding models having good task transfer performance. Model variants allow for trade-offs between accuracy and compute resources. We report the relationship between model complexity, resources, and transfer performance. Comparisons are made with baselines without transfer learning and to baselines that incorporate word-level transfer. Transfer learning using sentence-level embeddings is shown to outperform models without transfer learning and often those that use only word-level transfer. We show good transfer task performance with minimal training data and obtain encouraging results on word embedding association tests (WEAT) of model bias.</abstract>
<identifier type="citekey">cer-etal-2018-universal</identifier>
<identifier type="doi">10.18653/v1/D18-2029</identifier>
<location>
<url>https://aclanthology.org/D18-2029</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>169</start>
<end>174</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Universal Sentence Encoder for English
%A Cer, Daniel
%A Yang, Yinfei
%A Kong, Sheng-yi
%A Hua, Nan
%A Limtiaco, Nicole
%A St. John, Rhomni
%A Constant, Noah
%A Guajardo-Cespedes, Mario
%A Yuan, Steve
%A Tar, Chris
%A Strope, Brian
%A Kurzweil, Ray
%Y Blanco, Eduardo
%Y Lu, Wei
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F cer-etal-2018-universal
%X We present easy-to-use TensorFlow Hub sentence embedding models having good task transfer performance. Model variants allow for trade-offs between accuracy and compute resources. We report the relationship between model complexity, resources, and transfer performance. Comparisons are made with baselines without transfer learning and to baselines that incorporate word-level transfer. Transfer learning using sentence-level embeddings is shown to outperform models without transfer learning and often those that use only word-level transfer. We show good transfer task performance with minimal training data and obtain encouraging results on word embedding association tests (WEAT) of model bias.
%R 10.18653/v1/D18-2029
%U https://aclanthology.org/D18-2029
%U https://doi.org/10.18653/v1/D18-2029
%P 169-174
Markdown (Informal)
[Universal Sentence Encoder for English](https://aclanthology.org/D18-2029) (Cer et al., EMNLP 2018)
ACL
- Daniel Cer, Yinfei Yang, Sheng-yi Kong, Nan Hua, Nicole Limtiaco, Rhomni St. John, Noah Constant, Mario Guajardo-Cespedes, Steve Yuan, Chris Tar, Brian Strope, and Ray Kurzweil. 2018. Universal Sentence Encoder for English. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 169–174, Brussels, Belgium. Association for Computational Linguistics.