- Anthology ID:
- 2023.conll-babylm.30
- Volume:
- Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Alex Warstadt, Aaron Mueller, Leshem Choshen, Ethan Wilcox, Chengxu Zhuang, Juan Ciro, Rafael Mosquera, Bhargavi Paranjabe, Adina Williams, Tal Linzen, Ryan Cotterell
- Venue:
- CoNLL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 339–345
- Language:
- URL:
- https://aclanthology.org/2023.conll-babylm.30
- DOI:
- 10.18653/v1/2023.conll-babylm.30
- Bibkey:
- Cite (ACL):
- Khushi Bhardwaj, Raj Sanjay Shah, and Sashank Varma. 2023. Pre-training LLMs using human-like development data corpus. In Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning, pages 339–345, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Pre-training LLMs using human-like development data corpus (Bhardwaj et al., CoNLL 2023)
- Copy Citation:
- PDF:
- https://aclanthology.org/2023.conll-babylm.30.pdf
Export citation
@inproceedings{bhardwaj-etal-2023-pre,
title = "Pre-training {LLM}s using human-like development data corpus",
author = "Bhardwaj, Khushi and
Shah, Raj Sanjay and
Varma, Sashank",
editor = "Warstadt, Alex and
Mueller, Aaron and
Choshen, Leshem and
Wilcox, Ethan and
Zhuang, Chengxu and
Ciro, Juan and
Mosquera, Rafael and
Paranjabe, Bhargavi and
Williams, Adina and
Linzen, Tal and
Cotterell, Ryan",
booktitle = "Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.conll-babylm.30",
doi = "10.18653/v1/2023.conll-babylm.30",
pages = "339--345",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhardwaj-etal-2023-pre">
<titleInfo>
<title>Pre-training LLMs using human-like development data corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khushi</namePart>
<namePart type="family">Bhardwaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="given">Sanjay</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sashank</namePart>
<namePart type="family">Varma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Warstadt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="family">Wilcox</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengxu</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Ciro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Mosquera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhargavi</namePart>
<namePart type="family">Paranjabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adina</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<identifier type="citekey">bhardwaj-etal-2023-pre</identifier>
<identifier type="doi">10.18653/v1/2023.conll-babylm.30</identifier>
<location>
<url>https://aclanthology.org/2023.conll-babylm.30</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>339</start>
<end>345</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T Pre-training LLMs using human-like development data corpus %A Bhardwaj, Khushi %A Shah, Raj Sanjay %A Varma, Sashank %Y Warstadt, Alex %Y Mueller, Aaron %Y Choshen, Leshem %Y Wilcox, Ethan %Y Zhuang, Chengxu %Y Ciro, Juan %Y Mosquera, Rafael %Y Paranjabe, Bhargavi %Y Williams, Adina %Y Linzen, Tal %Y Cotterell, Ryan %S Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning %D 2023 %8 December %I Association for Computational Linguistics %C Singapore %F bhardwaj-etal-2023-pre %R 10.18653/v1/2023.conll-babylm.30 %U https://aclanthology.org/2023.conll-babylm.30 %U https://doi.org/10.18653/v1/2023.conll-babylm.30 %P 339-345
Markdown (Informal)
[Pre-training LLMs using human-like development data corpus](https://aclanthology.org/2023.conll-babylm.30) (Bhardwaj et al., CoNLL 2023)
- Pre-training LLMs using human-like development data corpus (Bhardwaj et al., CoNLL 2023)
ACL
- Khushi Bhardwaj, Raj Sanjay Shah, and Sashank Varma. 2023. Pre-training LLMs using human-like development data corpus. In Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning, pages 339–345, Singapore. Association for Computational Linguistics.