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

TL;DR

SemSup-XC introduces a novel semantic supervision approach for zero and few-shot extreme classification, leveraging class descriptions and a hybrid matching module to achieve state-of-the-art results across diverse datasets.

Contribution

The paper presents SemSup-XC, a new model that uses semantic class descriptions and a hybrid matching module for improved zero and few-shot extreme classification.

Findings

Achieves up to 12 precision points improvement in zero-shot classification.

Outperforms baselines on three diverse datasets.

Highlights importance of hybrid matching and semantic descriptions.

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.