How does the task complexity of masked pretraining objectives affect downstream performance?
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AUHFEIXJP" target="_blank" >RIV/00216208:11320/23:UHFEIXJP - isvavai.cz</a>
Výsledek na webu
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175439688&partnerID=40&md5=0eb598059f3ef78ab89fa48116651a54" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175439688&partnerID=40&md5=0eb598059f3ef78ab89fa48116651a54</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
How does the task complexity of masked pretraining objectives affect downstream performance?
Popis výsledku v původním jazyce
"Masked language modeling (MLM) is a widely used self-supervised pretraining objective, where a model needs to predict an original token that is replaced with a mask given contexts. Although simpler and computationally efficient pretraining objectives, e.g., predicting the first character of a masked token, have recently shown comparable results to MLM, no objectives with a masking scheme actually outperform it in downstream tasks. Motivated by the assumption that their lack of complexity plays a vital role in the degradation, we validate whether more complex masked objectives can achieve better results and investigate how much complexity they should have to perform comparably to MLM. Our results using GLUE, SQuAD, and Universal Dependencies benchmarks demonstrate that more complicated objectives tend to show better downstream results with at least half of the MLM complexity needed to perform comparably to MLM. Finally, we discuss how we should pretrain a model using a masked objective from the task complexity perspective. © 2023 Association for Computational Linguistics."
Název v anglickém jazyce
How does the task complexity of masked pretraining objectives affect downstream performance?
Popis výsledku anglicky
"Masked language modeling (MLM) is a widely used self-supervised pretraining objective, where a model needs to predict an original token that is replaced with a mask given contexts. Although simpler and computationally efficient pretraining objectives, e.g., predicting the first character of a masked token, have recently shown comparable results to MLM, no objectives with a masking scheme actually outperform it in downstream tasks. Motivated by the assumption that their lack of complexity plays a vital role in the degradation, we validate whether more complex masked objectives can achieve better results and investigate how much complexity they should have to perform comparably to MLM. Our results using GLUE, SQuAD, and Universal Dependencies benchmarks demonstrate that more complicated objectives tend to show better downstream results with at least half of the MLM complexity needed to perform comparably to MLM. Finally, we discuss how we should pretrain a model using a masked objective from the task complexity perspective. © 2023 Association for Computational Linguistics."
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
—
Návaznosti
—
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
"Proc. Annu. Meet. Assoc. Comput Linguist."
ISBN
978-195942962-3
ISSN
0736-587X
e-ISSN
—
Počet stran výsledku
11
Strana od-do
10527-10537
Název nakladatele
Association for Computational Linguistics (ACL)
Místo vydání
—
Místo konání akce
Dubrovnik
Datum konání akce
1. 1. 2023
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—