A Simple Log-based Loss Function for Ordinal Text Classification
The cross-entropy loss function is widely used and generally considered the default loss function for text classification. When it comes to ordinal text classification where there is an ordinal relationship between labels, the cross-entropy is not optimal as it does not incorporate the ordinal character into its feedback. In this paper, we propose a new simple loss function called ordinal log-loss (OLL). We show that this loss function outperforms state-of-the-art previously introduced losses on four benchmark text classification datasets.
Code (1)
Tasks
Classificationtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
A simple log-based loss function for ordinal text classification
The cross-entropy loss function is widely used and generally considered the default loss function for text classification. When it comes to ordinal text classification where there is an ordinal relationship between label…
Classificationtext-classificationText ClassificationDeep Neural Networks with Ordinal Loss for Medical Applications
In many prediction problems in medical applications, target labels exhibit an inherent ordinal structure, where class ordering reflects clinically meaningful severity levels. The cost associated with misclassification is…
A simple squared-error reformulation for ordinal classification
In this paper, we explore ordinal classification (in the context of deep neural networks) through a simple modification of the squared error loss which not only allows it to not only be sensitive to class ordering, but a…
ClassificationGeneral ClassificationOrdinal ClassificationXL-DURel: Finetuning Sentence Transformers for Ordinal Word-in-Context Classification
We propose XL-DURel, a finetuned, multilingual Sentence Transformer model optimized for ordinal Word-in-Context classification. We test several loss functions for regression and ranking tasks managing to outperform previ…
On the Consistency of Ordinal Regression Methods
Many of the ordinal regression models that have been proposed in the literature can be seen as methods that minimize a convex surrogate of the zero-one, absolute, or squared loss functions. A key property that allows to …
Binary ClassificationGeneral Classificationregression