Can Triplet Loss Be Used for Multi-Label Few-Shot Classification? A Case Study
Few-shot learning is a deep learning subfield that is the focus of research nowadays. This paper addresses the research question of whether a triplet-trained Siamese network, initially designed for multi-class classification, can effectively handle multi-label classification. We conducted a case stu...
Elmentve itt :
| Szerzők: | |
|---|---|
| Dokumentumtípus: | Cikk |
| Megjelent: |
2023
|
| Sorozat: | INFORMATION (BASEL)
14 No. 10 |
| Tárgyszavak: | |
| doi: | 10.3390/info14100520 |
| mtmt: | 34154749 |
| Online Access: | http://publicatio.bibl.u-szeged.hu/28332 |
| Tartalmi kivonat: | Few-shot learning is a deep learning subfield that is the focus of research nowadays. This paper addresses the research question of whether a triplet-trained Siamese network, initially designed for multi-class classification, can effectively handle multi-label classification. We conducted a case study to identify any limitations in its application. The experiments were conducted on a dataset containing Hungarian legal decisions of administrative agencies in tax matters belonging to a major legal content provider. We also tested how different Siamese embeddings compare on classifying a previously non-existing label on a binary and a multi-label setting. We found that triplet-trained Siamese networks can be applied to perform classification but with a sampling restriction during training. We also found that the overlap between labels affects the results negatively. The few-shot model, seeing only ten examples for each label, provided competitive results compared to models trained on tens of thousands of court decisions using tf-idf vectorization and logistic regression. |
|---|---|
| Terjedelem/Fizikai jellemzők: | 17 |
| ISSN: | 2078-2489 |