SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification

Pranjal Aggarwal, Ameet Deshpande, Karthik R Narasimhan
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:228-247, 2023.

Abstract

Extreme classification (XC) involves predicting over large numbers of classes (thousands to millions), with real-world applications like news article classification and e-commerce product tagging. The zero-shot version of this task requires generalization to novel classes without additional supervision. In this paper, we develop SemSup-XC, a model that achieves state-of-the-art zero-shot and few-shot performance on three XC datasets derived from legal, e-commerce, and Wikipedia data. To develop SemSup-XC, we use automatically collected semantic class descriptions to represent classes and facilitate generalization through a novel hybrid matching module that matches input instances to class descriptions using a combination of semantic and lexical similarity. Trained with contrastive learning, SemSup-XC significantly outperforms baselines and establishes state-of-the-art performance on all three datasets considered, gaining up to 12 precision points on zero-shot and more than 10 precision points on one-shot tests, with similar gains for recall@10. Our ablation studies highlight the relative importance of our hybrid matching module and automatically collected class descriptions.

Cite this Paper


BibTeX
@InProceedings{pmlr-v202-aggarwal23a, title = {{S}em{S}up-{XC}: Semantic Supervision for Zero and Few-shot Extreme Classification}, author = {Aggarwal, Pranjal and Deshpande, Ameet and Narasimhan, Karthik R}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {228--247}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/aggarwal23a/aggarwal23a.pdf}, url = {https://proceedings.mlr.press/v202/aggarwal23a.html}, abstract = {Extreme classification (XC) involves predicting over large numbers of classes (thousands to millions), with real-world applications like news article classification and e-commerce product tagging. The zero-shot version of this task requires generalization to novel classes without additional supervision. In this paper, we develop SemSup-XC, a model that achieves state-of-the-art zero-shot and few-shot performance on three XC datasets derived from legal, e-commerce, and Wikipedia data. To develop SemSup-XC, we use automatically collected semantic class descriptions to represent classes and facilitate generalization through a novel hybrid matching module that matches input instances to class descriptions using a combination of semantic and lexical similarity. Trained with contrastive learning, SemSup-XC significantly outperforms baselines and establishes state-of-the-art performance on all three datasets considered, gaining up to 12 precision points on zero-shot and more than 10 precision points on one-shot tests, with similar gains for recall@10. Our ablation studies highlight the relative importance of our hybrid matching module and automatically collected class descriptions.} }
Endnote
%0 Conference Paper %T SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification %A Pranjal Aggarwal %A Ameet Deshpande %A Karthik R Narasimhan %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-aggarwal23a %I PMLR %P 228--247 %U https://proceedings.mlr.press/v202/aggarwal23a.html %V 202 %X Extreme classification (XC) involves predicting over large numbers of classes (thousands to millions), with real-world applications like news article classification and e-commerce product tagging. The zero-shot version of this task requires generalization to novel classes without additional supervision. In this paper, we develop SemSup-XC, a model that achieves state-of-the-art zero-shot and few-shot performance on three XC datasets derived from legal, e-commerce, and Wikipedia data. To develop SemSup-XC, we use automatically collected semantic class descriptions to represent classes and facilitate generalization through a novel hybrid matching module that matches input instances to class descriptions using a combination of semantic and lexical similarity. Trained with contrastive learning, SemSup-XC significantly outperforms baselines and establishes state-of-the-art performance on all three datasets considered, gaining up to 12 precision points on zero-shot and more than 10 precision points on one-shot tests, with similar gains for recall@10. Our ablation studies highlight the relative importance of our hybrid matching module and automatically collected class descriptions.
APA
Aggarwal, P., Deshpande, A. & Narasimhan, K.R.. (2023). SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:228-247 Available from https://proceedings.mlr.press/v202/aggarwal23a.html.

Related Material