@inproceedings{chen-etal-2024-open,
title = "Open-Set Semi-Supervised Text Classification via Adversarial Disagreement Maximization",
author = "Chen, Junfan and
Zhang, Richong and
Chen, Junchi and
Hu, Chunming",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-long.118/",
doi = "10.18653/v1/2024.acl-long.118",
pages = "2170--2180",
abstract = "Open-Set Semi-Supervised Text Classification (OSTC) aims to train a classification model on a limited set of labeled texts, alongside plenty of unlabeled texts that include both in-distribution and out-of-distribution examples. In this paper, we revisit the main challenge in OSTC, i.e., outlier detection, from a measurement disagreement perspective and innovatively propose to improve OSTC performance by directly maximizing the measurement disagreements. Based on the properties of in-measurement and cross-measurements, we design an Adversarial Disagreement Maximization (ADM) model that synergeticly optimizes the measurement disagreements. In addition, we develop an abnormal example detection and measurement calibration approach to guarantee the effectiveness of ADM training. Experiment results and comprehensive analysis of three benchmarks demonstrate the effectiveness of our model."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-open">
<titleInfo>
<title>Open-Set Semi-Supervised Text Classification via Adversarial Disagreement Maximization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junfan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junchi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunming</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Open-Set Semi-Supervised Text Classification (OSTC) aims to train a classification model on a limited set of labeled texts, alongside plenty of unlabeled texts that include both in-distribution and out-of-distribution examples. In this paper, we revisit the main challenge in OSTC, i.e., outlier detection, from a measurement disagreement perspective and innovatively propose to improve OSTC performance by directly maximizing the measurement disagreements. Based on the properties of in-measurement and cross-measurements, we design an Adversarial Disagreement Maximization (ADM) model that synergeticly optimizes the measurement disagreements. In addition, we develop an abnormal example detection and measurement calibration approach to guarantee the effectiveness of ADM training. Experiment results and comprehensive analysis of three benchmarks demonstrate the effectiveness of our model.</abstract>
<identifier type="citekey">chen-etal-2024-open</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.118</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-long.118/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>2170</start>
<end>2180</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Open-Set Semi-Supervised Text Classification via Adversarial Disagreement Maximization
%A Chen, Junfan
%A Zhang, Richong
%A Chen, Junchi
%A Hu, Chunming
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F chen-etal-2024-open
%X Open-Set Semi-Supervised Text Classification (OSTC) aims to train a classification model on a limited set of labeled texts, alongside plenty of unlabeled texts that include both in-distribution and out-of-distribution examples. In this paper, we revisit the main challenge in OSTC, i.e., outlier detection, from a measurement disagreement perspective and innovatively propose to improve OSTC performance by directly maximizing the measurement disagreements. Based on the properties of in-measurement and cross-measurements, we design an Adversarial Disagreement Maximization (ADM) model that synergeticly optimizes the measurement disagreements. In addition, we develop an abnormal example detection and measurement calibration approach to guarantee the effectiveness of ADM training. Experiment results and comprehensive analysis of three benchmarks demonstrate the effectiveness of our model.
%R 10.18653/v1/2024.acl-long.118
%U https://aclanthology.org/2024.luhme-long.118/
%U https://doi.org/10.18653/v1/2024.acl-long.118
%P 2170-2180
Markdown (Informal)
[Open-Set Semi-Supervised Text Classification via Adversarial Disagreement Maximization](https://aclanthology.org/2024.luhme-long.118/) (Chen et al., ACL 2024)
ACL