@inproceedings{wang-etal-2026-solve,
title = "How to Solve Noise and Hard Samples: Filtering and Difficulty-adaptive Augmentation for Fine-grained Negative Emotion Classification",
author = "Wang, Lianxi and
Lin, Siting and
Liang, Chao and
Li, Yuying and
Liao, Xinfeng and
Lin, Nankai",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2558/",
pages = "58138--58156",
ISBN = "979-8-89176-459-0",
abstract = "Fine-grained negative emotion classification suffers from subjective annotation noise and semantically ambiguous hard samples, which severely degrades model performance. Most existing methods cannot distinguish valid hard samples from noise and lack strategies to improve hard sample learnability. To address these issues, we propose a Noise Filtering and Difficulty-adaptive Hard Sample Augmentation (NF-DHSA) framework for fine-grained negative emotion classification. It first mines high-risk candidates using a hybrid score of normalized loss and predictive entropy, then applies a multi-view logic-guided filtering mechanism to reliably separate noise from valid hard samples. Further, difficulty-adaptive dynamic augmentation generates moderate-difficulty, label-stable augmented samples, and prototype-guided dual-granularity contrastive learning aligns original-augmented pairs while strengthening global category boundaries. The results reported on three benchmark datasets show that NF-DHSA outperforms the baseline methods overall, with Macro-F1 scores improved by 1.25{\%}, 2.47{\%}, and 3.53{\%} on the VIRUS, NLPCC, and COVID datasets, respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-solve">
<titleInfo>
<title>How to Solve Noise and Hard Samples: Filtering and Difficulty-adaptive Augmentation for Fine-grained Negative Emotion Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lianxi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siting</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuying</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinfeng</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nankai</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Fine-grained negative emotion classification suffers from subjective annotation noise and semantically ambiguous hard samples, which severely degrades model performance. Most existing methods cannot distinguish valid hard samples from noise and lack strategies to improve hard sample learnability. To address these issues, we propose a Noise Filtering and Difficulty-adaptive Hard Sample Augmentation (NF-DHSA) framework for fine-grained negative emotion classification. It first mines high-risk candidates using a hybrid score of normalized loss and predictive entropy, then applies a multi-view logic-guided filtering mechanism to reliably separate noise from valid hard samples. Further, difficulty-adaptive dynamic augmentation generates moderate-difficulty, label-stable augmented samples, and prototype-guided dual-granularity contrastive learning aligns original-augmented pairs while strengthening global category boundaries. The results reported on three benchmark datasets show that NF-DHSA outperforms the baseline methods overall, with Macro-F1 scores improved by 1.25%, 2.47%, and 3.53% on the VIRUS, NLPCC, and COVID datasets, respectively.</abstract>
<identifier type="citekey">wang-etal-2026-solve</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2558/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>58138</start>
<end>58156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How to Solve Noise and Hard Samples: Filtering and Difficulty-adaptive Augmentation for Fine-grained Negative Emotion Classification
%A Wang, Lianxi
%A Lin, Siting
%A Liang, Chao
%A Li, Yuying
%A Liao, Xinfeng
%A Lin, Nankai
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F wang-etal-2026-solve
%X Fine-grained negative emotion classification suffers from subjective annotation noise and semantically ambiguous hard samples, which severely degrades model performance. Most existing methods cannot distinguish valid hard samples from noise and lack strategies to improve hard sample learnability. To address these issues, we propose a Noise Filtering and Difficulty-adaptive Hard Sample Augmentation (NF-DHSA) framework for fine-grained negative emotion classification. It first mines high-risk candidates using a hybrid score of normalized loss and predictive entropy, then applies a multi-view logic-guided filtering mechanism to reliably separate noise from valid hard samples. Further, difficulty-adaptive dynamic augmentation generates moderate-difficulty, label-stable augmented samples, and prototype-guided dual-granularity contrastive learning aligns original-augmented pairs while strengthening global category boundaries. The results reported on three benchmark datasets show that NF-DHSA outperforms the baseline methods overall, with Macro-F1 scores improved by 1.25%, 2.47%, and 3.53% on the VIRUS, NLPCC, and COVID datasets, respectively.
%U https://aclanthology.org/2026.emnlp-main.2558/
%P 58138-58156
Markdown (Informal)
[How to Solve Noise and Hard Samples: Filtering and Difficulty-adaptive Augmentation for Fine-grained Negative Emotion Classification](https://aclanthology.org/2026.emnlp-main.2558/) (Wang et al., EMNLP 2026)
ACL