@inproceedings{sedova-roth-2023-ulf,
title = "{ULF}: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision",
author = "Sedova, Anastasiia and
Roth, Benjamin",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.254",
doi = "10.18653/v1/2023.emnlp-main.254",
pages = "4162--4176",
abstract = "A cost-effective alternative to manual data labeling is weak supervision (WS), where data samples are automatically annotated using a predefined set of labeling functions (LFs), rule-based mechanisms that generate artificial labels for the associated classes. In this work, we investigate noise reduction techniques for WS based on the principle of k-fold cross-validation. We introduce a new algorithm ULF for Unsupervised Labeling Function correction, which denoises WS data by leveraging models trained on all but some LFs to identify and correct biases specific to the held-out LFs. Specifically, ULF refines the allocation of LFs to classes by re-estimating this assignment on highly reliable cross-validated samples. Evaluation on multiple datasets confirms ULF{'}s effectiveness in enhancing WS learning without the need for manual labeling.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sedova-roth-2023-ulf">
<titleInfo>
<title>ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastasiia</namePart>
<namePart type="family">Sedova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A cost-effective alternative to manual data labeling is weak supervision (WS), where data samples are automatically annotated using a predefined set of labeling functions (LFs), rule-based mechanisms that generate artificial labels for the associated classes. In this work, we investigate noise reduction techniques for WS based on the principle of k-fold cross-validation. We introduce a new algorithm ULF for Unsupervised Labeling Function correction, which denoises WS data by leveraging models trained on all but some LFs to identify and correct biases specific to the held-out LFs. Specifically, ULF refines the allocation of LFs to classes by re-estimating this assignment on highly reliable cross-validated samples. Evaluation on multiple datasets confirms ULF’s effectiveness in enhancing WS learning without the need for manual labeling.</abstract>
<identifier type="citekey">sedova-roth-2023-ulf</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.254</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.254</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>4162</start>
<end>4176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision
%A Sedova, Anastasiia
%A Roth, Benjamin
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F sedova-roth-2023-ulf
%X A cost-effective alternative to manual data labeling is weak supervision (WS), where data samples are automatically annotated using a predefined set of labeling functions (LFs), rule-based mechanisms that generate artificial labels for the associated classes. In this work, we investigate noise reduction techniques for WS based on the principle of k-fold cross-validation. We introduce a new algorithm ULF for Unsupervised Labeling Function correction, which denoises WS data by leveraging models trained on all but some LFs to identify and correct biases specific to the held-out LFs. Specifically, ULF refines the allocation of LFs to classes by re-estimating this assignment on highly reliable cross-validated samples. Evaluation on multiple datasets confirms ULF’s effectiveness in enhancing WS learning without the need for manual labeling.
%R 10.18653/v1/2023.emnlp-main.254
%U https://aclanthology.org/2023.emnlp-main.254
%U https://doi.org/10.18653/v1/2023.emnlp-main.254
%P 4162-4176
Markdown (Informal)
[ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision](https://aclanthology.org/2023.emnlp-main.254) (Sedova & Roth, EMNLP 2023)
ACL