@inproceedings{behr-2024-elc,
title = "{ELC}-{P}arser{BERT}: Low-Resource Language Modeling Utilizing a Parser Network With {ELC}-{BERT}",
author = "Behr, Rufus",
editor = "Hu, Michael Y. and
Mueller, Aaron and
Ross, Candace and
Williams, Adina and
Linzen, Tal and
Zhuang, Chengxu and
Choshen, Leshem and
Cotterell, Ryan and
Warstadt, Alex and
Wilcox, Ethan Gotlieb",
booktitle = "The 2nd BabyLM Challenge at the 28th Conference on Computational Natural Language Learning",
month = nov,
year = "2024",
address = "Miami, FL, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.conll-babylm.11/",
pages = "140--146",
abstract = "This paper investigates the effect of including a parser network, which produces syntactic heights and distances to perform unsupervised parsing, in the Every Layer Counts BERT (ELC-BERT) architecture trained on 10M tokens for the 2024 BabyLM challenge. The parser network`s inclusion in this setup shows little or no improvement over the ELC-BERT baseline for the BLiMP and GLUE evaluation, but, in particular domains of the EWoK evaluation framework, its inclusion shows promise for improvement and raises interesting questions about its effect on learning different concepts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="behr-2024-elc">
<titleInfo>
<title>ELC-ParserBERT: Low-Resource Language Modeling Utilizing a Parser Network With ELC-BERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rufus</namePart>
<namePart type="family">Behr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 2nd BabyLM Challenge at the 28th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">Y</namePart>
<namePart type="family">Hu</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">Candace</namePart>
<namePart type="family">Ross</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">Chengxu</namePart>
<namePart type="family">Zhuang</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">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Ethan</namePart>
<namePart type="given">Gotlieb</namePart>
<namePart type="family">Wilcox</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, FL, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper investigates the effect of including a parser network, which produces syntactic heights and distances to perform unsupervised parsing, in the Every Layer Counts BERT (ELC-BERT) architecture trained on 10M tokens for the 2024 BabyLM challenge. The parser network‘s inclusion in this setup shows little or no improvement over the ELC-BERT baseline for the BLiMP and GLUE evaluation, but, in particular domains of the EWoK evaluation framework, its inclusion shows promise for improvement and raises interesting questions about its effect on learning different concepts.</abstract>
<identifier type="citekey">behr-2024-elc</identifier>
<location>
<url>https://aclanthology.org/2024.conll-babylm.11/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>140</start>
<end>146</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ELC-ParserBERT: Low-Resource Language Modeling Utilizing a Parser Network With ELC-BERT
%A Behr, Rufus
%Y Hu, Michael Y.
%Y Mueller, Aaron
%Y Ross, Candace
%Y Williams, Adina
%Y Linzen, Tal
%Y Zhuang, Chengxu
%Y Choshen, Leshem
%Y Cotterell, Ryan
%Y Warstadt, Alex
%Y Wilcox, Ethan Gotlieb
%S The 2nd BabyLM Challenge at the 28th Conference on Computational Natural Language Learning
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F behr-2024-elc
%X This paper investigates the effect of including a parser network, which produces syntactic heights and distances to perform unsupervised parsing, in the Every Layer Counts BERT (ELC-BERT) architecture trained on 10M tokens for the 2024 BabyLM challenge. The parser network‘s inclusion in this setup shows little or no improvement over the ELC-BERT baseline for the BLiMP and GLUE evaluation, but, in particular domains of the EWoK evaluation framework, its inclusion shows promise for improvement and raises interesting questions about its effect on learning different concepts.
%U https://aclanthology.org/2024.conll-babylm.11/
%P 140-146
Markdown (Informal)
[ELC-ParserBERT: Low-Resource Language Modeling Utilizing a Parser Network With ELC-BERT](https://aclanthology.org/2024.conll-babylm.11/) (Behr, CoNLL-BabyLM 2024)
ACL