{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/label-semantic-aware-pre-training-for-few","title":"Label Semantic Aware Pre-training for Few-shot Text Classification","arxiv_id":"2204.07128","date":"2022-04-14","proceeding":"ACL 2022 5","authors":["Aaron Mueller","Jason Krone","Salvatore Romeo","Saab Mansour","Elman Mansimov","Yi Zhang","Dan Roth"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2204.07128v2","url_pdf":"https://arxiv.org/pdf/2204.07128v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"label-semantic-aware-pre-training-for-few","repo_url":"https://github.com/amazon-research/label-aware-pretrain","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"few-shot-text-classification","task_name":"Few-Shot Text Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"topic-classification","task_name":"Topic Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"aware","method_name":"AWARE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.07128","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}