Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911838631886848 |
|---|---|
| author | Audibert, Alexandre Gauffre, Aurélien Amini, Massih-Reza |
| author_facet | Audibert, Alexandre Gauffre, Aurélien Amini, Massih-Reza |
| contents | Learning an effective representation in multi-label text classification (MLTC) is a significant challenge in NLP. This challenge arises from the inherent complexity of the task, which is shaped by two key factors: the intricate connections between labels and the widespread long-tailed distribution of the data. To overcome this issue, one potential approach involves integrating supervised contrastive learning with classical supervised loss functions. Although contrastive learning has shown remarkable performance in multi-class classification, its impact in the multi-label framework has not been thoroughly investigated. In this paper, we conduct an in-depth study of supervised contrastive learning and its influence on representation in MLTC context. We emphasize the importance of considering long-tailed data distributions to build a robust representation space, which effectively addresses two critical challenges associated with contrastive learning that we identify: the "lack of positives" and the "attraction-repulsion imbalance". Building on this insight, we introduce a novel contrastive loss function for MLTC. It attains Micro-F1 scores that either match or surpass those obtained with other frequently employed loss functions, and demonstrates a significant improvement in Macro-F1 scores across three multi-label datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08720 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification Audibert, Alexandre Gauffre, Aurélien Amini, Massih-Reza Machine Learning Computation and Language Information Retrieval Learning an effective representation in multi-label text classification (MLTC) is a significant challenge in NLP. This challenge arises from the inherent complexity of the task, which is shaped by two key factors: the intricate connections between labels and the widespread long-tailed distribution of the data. To overcome this issue, one potential approach involves integrating supervised contrastive learning with classical supervised loss functions. Although contrastive learning has shown remarkable performance in multi-class classification, its impact in the multi-label framework has not been thoroughly investigated. In this paper, we conduct an in-depth study of supervised contrastive learning and its influence on representation in MLTC context. We emphasize the importance of considering long-tailed data distributions to build a robust representation space, which effectively addresses two critical challenges associated with contrastive learning that we identify: the "lack of positives" and the "attraction-repulsion imbalance". Building on this insight, we introduce a novel contrastive loss function for MLTC. It attains Micro-F1 scores that either match or surpass those obtained with other frequently employed loss functions, and demonstrates a significant improvement in Macro-F1 scores across three multi-label datasets. |
| title | Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification |
| topic | Machine Learning Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2404.08720 |