Papers › Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution

Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution

10 Sep 2021EMNLP 2021 11arXiv:2109.04712archive 2025-07-28

Yi Huang, Buse Giledereli, Abdullatif Köksal, Arzucan Özgür, Elif Ozkirimli

Multi-label text classification is a challenging task because it requires capturing label dependencies. It becomes even more challenging when class distribution is long-tailed. Resampling and re-weighting are common approaches used for addressing the class imbalance problem, however, they are not effective when there is label dependency besides class imbalance because they result in oversampling of common labels. Here, we introduce the application of balancing loss functions for multi-label text classification. We perform experiments on a general domain dataset with 90 labels (Reuters-21578) and a domain-specific dataset from PubMed with 18211 labels. We find that a distribution-balanced loss function, which inherently addresses both the class imbalance and label linkage problems, outperforms commonly used loss functions. Distribution balancing methods have been successfully used in the image recognition field. Here, we show their effectiveness in natural language processing. Source code is available at https://github.com/Roche/BalancedLossNLP.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Roche/BalancedLossNLP officialmentioned in papermentioned on GitHubpytorch report
blessu/balancedlossnlp officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Document ClassificationMulti-Label Text ClassificationText Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Label Text Classification Reuters-21578 CB-NTR Micro-F1 90.74 #2 of 7 Archive leaderboard report
Multi-Label Text Classification Reuters-21578 NTR-FL Micro-F1 90.70 #3 of 7 Archive leaderboard report
Multi-Label Text Classification Reuters-21578 DB Micro-F1 90.62 #4 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections