@inproceedings{vahtola-etal-2022-modeling,
title = "Modeling Noise in Paraphrase Detection",
author = {Vahtola, Teemu and
Sj{\"o}blom, Eetu and
Tiedemann, J{\"o}rg and
Creutz, Mathias},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.461",
pages = "4324--4332",
abstract = "Noisy labels in training data present a challenging issue in classification tasks, misleading a model towards incorrect decisions during training. In this paper, we propose the use of a linear noise model to augment pre-trained language models to account for label noise in fine-tuning. We test our approach in a paraphrase detection task with various levels of noise and five different languages. Our experiments demonstrate the effectiveness of the additional noise model in making the training procedures more robust and stable. Furthermore, we show that this model can be applied without further knowledge about annotation confidence and reliability of individual training examples and we analyse our results in light of data selection and sampling strategies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vahtola-etal-2022-modeling">
<titleInfo>
<title>Modeling Noise in Paraphrase Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Teemu</namePart>
<namePart type="family">Vahtola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eetu</namePart>
<namePart type="family">Sjöblom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathias</namePart>
<namePart type="family">Creutz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Noisy labels in training data present a challenging issue in classification tasks, misleading a model towards incorrect decisions during training. In this paper, we propose the use of a linear noise model to augment pre-trained language models to account for label noise in fine-tuning. We test our approach in a paraphrase detection task with various levels of noise and five different languages. Our experiments demonstrate the effectiveness of the additional noise model in making the training procedures more robust and stable. Furthermore, we show that this model can be applied without further knowledge about annotation confidence and reliability of individual training examples and we analyse our results in light of data selection and sampling strategies.</abstract>
<identifier type="citekey">vahtola-etal-2022-modeling</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.461</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4324</start>
<end>4332</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling Noise in Paraphrase Detection
%A Vahtola, Teemu
%A Sjöblom, Eetu
%A Tiedemann, Jörg
%A Creutz, Mathias
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F vahtola-etal-2022-modeling
%X Noisy labels in training data present a challenging issue in classification tasks, misleading a model towards incorrect decisions during training. In this paper, we propose the use of a linear noise model to augment pre-trained language models to account for label noise in fine-tuning. We test our approach in a paraphrase detection task with various levels of noise and five different languages. Our experiments demonstrate the effectiveness of the additional noise model in making the training procedures more robust and stable. Furthermore, we show that this model can be applied without further knowledge about annotation confidence and reliability of individual training examples and we analyse our results in light of data selection and sampling strategies.
%U https://aclanthology.org/2022.lrec-1.461
%P 4324-4332
Markdown (Informal)
[Modeling Noise in Paraphrase Detection](https://aclanthology.org/2022.lrec-1.461) (Vahtola et al., LREC 2022)
ACL
- Teemu Vahtola, Eetu Sjöblom, Jörg Tiedemann, and Mathias Creutz. 2022. Modeling Noise in Paraphrase Detection. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 4324–4332, Marseille, France. European Language Resources Association.