Abstract
Large multi-label datasets contain labels that occur thousands of times (frequent group), those that occur only a few times (few-shot group), and labels that never appear in the training dataset (zero-shot group). Multi-label few- and zero-shot label prediction is mostly unexplored on datasets with large label spaces, especially for text classification. In this paper, we perform a fine-grained evaluation to understand how state-of-the-art methods perform on infrequent labels. Furthermore, we develop few- and zero-shot methods for multi-label text classification when there is a known structure over the label space, and evaluate them on two publicly available medical text datasets: MIMIC II and MIMIC III. For few-shot labels we achieve improvements of 6.2% and 4.8% in R@10 for MIMIC II and MIMIC III, respectively, over prior efforts; the corresponding R@10 improvements for zero-shot labels are 17.3% and 19%.- Anthology ID:
- D18-1352
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3132–3142
- Language:
- URL:
- https://aclanthology.org/D18-1352
- DOI:
- 10.18653/v1/D18-1352
- Cite (ACL):
- Anthony Rios and Ramakanth Kavuluru. 2018. Few-Shot and Zero-Shot Multi-Label Learning for Structured Label Spaces. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3132–3142, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Few-Shot and Zero-Shot Multi-Label Learning for Structured Label Spaces (Rios & Kavuluru, EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/D18-1352.pdf
- Code
- bionlproc/multi-label-zero-shot