@inproceedings{bhattarai-erk-2024-learn,
title = "To Learn or Not to Learn: Replaced Token Detection for Learning the Meaning of Negation",
author = "Bhattarai, Gunjan and
Erk, Katrin",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1411",
pages = "16237--16250",
abstract = "State-of-the-art language models perform well on a variety of language tasks, but they continue to struggle with understanding negation cues in tasks like natural language inference (NLI). Inspired by Hossain et al. (2020), who show under-representation of negation in language model pretraining datasets, we experiment with additional pretraining with negation data for which we introduce two new datasets. We also introduce a new learning strategy for negation building on ELECTRA{'}s (Clark et al., 2020) replaced token detection objective. We find that continuing to pretrain ELECTRA-Small{'}s discriminator leads to substantial gains on a variant of RTE (Recognizing Textual Entailment) with additional negation. On SNLI (Stanford NLI) (Bowman et al., 2015), there are no gains due to the extreme under-representation of negation in the data. Finally, on MNLI (Multi-NLI) (Williams et al., 2018), we find that performance on negation cues is primarily stymied by neutral-labeled examples.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhattarai-erk-2024-learn">
<titleInfo>
<title>To Learn or Not to Learn: Replaced Token Detection for Learning the Meaning of Negation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gunjan</namePart>
<namePart type="family">Bhattarai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katrin</namePart>
<namePart type="family">Erk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>State-of-the-art language models perform well on a variety of language tasks, but they continue to struggle with understanding negation cues in tasks like natural language inference (NLI). Inspired by Hossain et al. (2020), who show under-representation of negation in language model pretraining datasets, we experiment with additional pretraining with negation data for which we introduce two new datasets. We also introduce a new learning strategy for negation building on ELECTRA’s (Clark et al., 2020) replaced token detection objective. We find that continuing to pretrain ELECTRA-Small’s discriminator leads to substantial gains on a variant of RTE (Recognizing Textual Entailment) with additional negation. On SNLI (Stanford NLI) (Bowman et al., 2015), there are no gains due to the extreme under-representation of negation in the data. Finally, on MNLI (Multi-NLI) (Williams et al., 2018), we find that performance on negation cues is primarily stymied by neutral-labeled examples.</abstract>
<identifier type="citekey">bhattarai-erk-2024-learn</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1411</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>16237</start>
<end>16250</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To Learn or Not to Learn: Replaced Token Detection for Learning the Meaning of Negation
%A Bhattarai, Gunjan
%A Erk, Katrin
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F bhattarai-erk-2024-learn
%X State-of-the-art language models perform well on a variety of language tasks, but they continue to struggle with understanding negation cues in tasks like natural language inference (NLI). Inspired by Hossain et al. (2020), who show under-representation of negation in language model pretraining datasets, we experiment with additional pretraining with negation data for which we introduce two new datasets. We also introduce a new learning strategy for negation building on ELECTRA’s (Clark et al., 2020) replaced token detection objective. We find that continuing to pretrain ELECTRA-Small’s discriminator leads to substantial gains on a variant of RTE (Recognizing Textual Entailment) with additional negation. On SNLI (Stanford NLI) (Bowman et al., 2015), there are no gains due to the extreme under-representation of negation in the data. Finally, on MNLI (Multi-NLI) (Williams et al., 2018), we find that performance on negation cues is primarily stymied by neutral-labeled examples.
%U https://aclanthology.org/2024.lrec-main.1411
%P 16237-16250
Markdown (Informal)
[To Learn or Not to Learn: Replaced Token Detection for Learning the Meaning of Negation](https://aclanthology.org/2024.lrec-main.1411) (Bhattarai & Erk, LREC-COLING 2024)
ACL