@inproceedings{agrawal-singh-2023-corpus,
title = "Corpus Complexity Matters in Pretraining Language Models",
author = "Agrawal, Ameeta and
Singh, Suresh",
editor = "Sadat Moosavi, Nafise and
Gurevych, Iryna and
Hou, Yufang and
Kim, Gyuwan and
Kim, Young Jin and
Schuster, Tal and
Agrawal, Ameeta",
booktitle = "Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP)",
month = jul,
year = "2023",
address = "Toronto, Canada (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sustainlp-1.20",
doi = "10.18653/v1/2023.sustainlp-1.20",
pages = "257--263",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agrawal-singh-2023-corpus">
<titleInfo>
<title>Corpus Complexity Matters in Pretraining Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ameeta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suresh</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nafise</namePart>
<namePart type="family">Sadat Moosavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufang</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gyuwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Young</namePart>
<namePart type="given">Jin</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Schuster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ameeta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<identifier type="citekey">agrawal-singh-2023-corpus</identifier>
<identifier type="doi">10.18653/v1/2023.sustainlp-1.20</identifier>
<location>
<url>https://aclanthology.org/2023.sustainlp-1.20</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>257</start>
<end>263</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus Complexity Matters in Pretraining Language Models
%A Agrawal, Ameeta
%A Singh, Suresh
%Y Sadat Moosavi, Nafise
%Y Gurevych, Iryna
%Y Hou, Yufang
%Y Kim, Gyuwan
%Y Kim, Young Jin
%Y Schuster, Tal
%Y Agrawal, Ameeta
%S Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada (Hybrid)
%F agrawal-singh-2023-corpus
%R 10.18653/v1/2023.sustainlp-1.20
%U https://aclanthology.org/2023.sustainlp-1.20
%U https://doi.org/10.18653/v1/2023.sustainlp-1.20
%P 257-263
Markdown (Informal)
[Corpus Complexity Matters in Pretraining Language Models](https://aclanthology.org/2023.sustainlp-1.20) (Agrawal & Singh, sustainlp 2023)
ACL
- Ameeta Agrawal and Suresh Singh. 2023. Corpus Complexity Matters in Pretraining Language Models. In Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP), pages 257–263, Toronto, Canada (Hybrid). Association for Computational Linguistics.