Buse Giledereli, Yi Huang, Abdullatif Köksal, Arzucan Özgür, Roche Müstahzarları, Elif Ozkirimli
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 multilabel 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/blessu/ BalancedLossNLP.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.04712")
get_code_for_paper("2109.04712")
have("2109.04712")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2109.04712.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2109.04712)
Connect an agent — have() is free.