@inproceedings{nijkamp-etal-2021-script,
title = "{SCRIPT}: Self-Critic {P}re{T}raining of Transformers",
author = "Nijkamp, Erik and
Pang, Bo and
Wu, Ying Nian and
Xiong, Caiming",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.409",
doi = "10.18653/v1/2021.naacl-main.409",
pages = "5196--5202",
abstract = "We introduce Self-CRItic Pretraining Transformers (SCRIPT) for representation learning of text. The popular masked language modeling (MLM) pretraining methods like BERT replace some tokens with [MASK] and an encoder is trained to recover them, while ELECTRA trains a discriminator to detect replaced tokens proposed by a generator. In contrast, we train a language model as in MLM and further derive a discriminator or critic on top of the encoder without using any additional parameters. That is, the model itself is a critic. SCRIPT combines MLM training and discriminative training for learning rich representations and compute- and sample-efficiency. We demonstrate improved sample-efficiency in pretraining and enhanced representations evidenced by improved downstream task performance on GLUE and SQuAD over strong baselines. Also, the self-critic scores can be directly used as pseudo-log-likelihood for efficient scoring.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nijkamp-etal-2021-script">
<titleInfo>
<title>SCRIPT: Self-Critic PreTraining of Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Nijkamp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Pang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="given">Nian</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caiming</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</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">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce Self-CRItic Pretraining Transformers (SCRIPT) for representation learning of text. The popular masked language modeling (MLM) pretraining methods like BERT replace some tokens with [MASK] and an encoder is trained to recover them, while ELECTRA trains a discriminator to detect replaced tokens proposed by a generator. In contrast, we train a language model as in MLM and further derive a discriminator or critic on top of the encoder without using any additional parameters. That is, the model itself is a critic. SCRIPT combines MLM training and discriminative training for learning rich representations and compute- and sample-efficiency. We demonstrate improved sample-efficiency in pretraining and enhanced representations evidenced by improved downstream task performance on GLUE and SQuAD over strong baselines. Also, the self-critic scores can be directly used as pseudo-log-likelihood for efficient scoring.</abstract>
<identifier type="citekey">nijkamp-etal-2021-script</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.409</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.409</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5196</start>
<end>5202</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SCRIPT: Self-Critic PreTraining of Transformers
%A Nijkamp, Erik
%A Pang, Bo
%A Wu, Ying Nian
%A Xiong, Caiming
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F nijkamp-etal-2021-script
%X We introduce Self-CRItic Pretraining Transformers (SCRIPT) for representation learning of text. The popular masked language modeling (MLM) pretraining methods like BERT replace some tokens with [MASK] and an encoder is trained to recover them, while ELECTRA trains a discriminator to detect replaced tokens proposed by a generator. In contrast, we train a language model as in MLM and further derive a discriminator or critic on top of the encoder without using any additional parameters. That is, the model itself is a critic. SCRIPT combines MLM training and discriminative training for learning rich representations and compute- and sample-efficiency. We demonstrate improved sample-efficiency in pretraining and enhanced representations evidenced by improved downstream task performance on GLUE and SQuAD over strong baselines. Also, the self-critic scores can be directly used as pseudo-log-likelihood for efficient scoring.
%R 10.18653/v1/2021.naacl-main.409
%U https://aclanthology.org/2021.naacl-main.409
%U https://doi.org/10.18653/v1/2021.naacl-main.409
%P 5196-5202
Markdown (Informal)
[SCRIPT: Self-Critic PreTraining of Transformers](https://aclanthology.org/2021.naacl-main.409) (Nijkamp et al., NAACL 2021)
ACL
- Erik Nijkamp, Bo Pang, Ying Nian Wu, and Caiming Xiong. 2021. SCRIPT: Self-Critic PreTraining of Transformers. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5196–5202, Online. Association for Computational Linguistics.