CLApr 14, 2022

Label Semantic Aware Pre-training for Few-shot Text Classification

arXiv:2204.07128v2646 citationsh-index: 98
Originality Incremental advance
AI Analysis

This addresses the challenge of data efficiency in text classification for domains like intent and topic classification, though it is incremental as it builds on existing pre-trained models.

The paper tackles the problem of few-shot text classification by incorporating label semantics into pre-training, resulting in significant accuracy improvements over state-of-the-art models in few-shot settings while maintaining comparable performance in high-resource scenarios.

In text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction. However, use of label-semantics during pre-training has not been extensively explored. We therefore propose Label Semantic Aware Pre-training (LSAP) to improve the generalization and data efficiency of text classification systems. LSAP incorporates label semantics into pre-trained generative models (T5 in our case) by performing secondary pre-training on labeled sentences from a variety of domains. As domain-general pre-training requires large amounts of data, we develop a filtering and labeling pipeline to automatically create sentence-label pairs from unlabeled text. We perform experiments on intent (ATIS, Snips, TOPv2) and topic classification (AG News, Yahoo! Answers). LSAP obtains significant accuracy improvements over state-of-the-art models for few-shot text classification while maintaining performance comparable to state of the art in high-resource settings.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes