Few-Shot and Zero-Shot Multi-Label Learning for Structured Label Spaces

Anthony Rios, Ramakanth Kavuluru


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
URL:
https://www.aclweb.org/anthology/D18-1352
DOI:
10.18653/v1/D18-1352
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/D18-1352.pdf
Video:
 https://vimeo.com/305948835