{"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/lime-weakly-supervised-text-classification-1","title":"LIME: Weakly-Supervised Text Classification Without Seeds","arxiv_id":"2210.06720","date":"2022-10-13","proceeding":"COLING 2022 10","authors":["Seongmin Park","Jihwa Lee"],"abstract":"In weakly-supervised text classification, only label names act as sources of supervision. Predominant approaches to weakly-supervised text classification utilize a two-phase framework, where test samples are first assigned pseudo-labels and are then used to train a neural text classifier. In most previous work, the pseudo-labeling step is dependent on obtaining seed words that best capture the relevance of each class label. We present LIME, a framework for weakly-supervised text classification that entirely replaces the brittle seed-word generation process with entailment-based pseudo-classification. We find that combining weakly-supervised classification and textual entailment mitigates shortcomings of both, resulting in a more streamlined and effective classification pipeline. With just an off-the-shelf textual entailment model, LIME outperforms recent baselines in weakly-supervised text classification and achieves state-of-the-art in 4 benchmarks. We open source our code at https://github.com/seongminp/LIME.","url_abs":"https://arxiv.org/abs/2210.06720v1","url_pdf":"https://arxiv.org/pdf/2210.06720v1.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":"lime-weakly-supervised-text-classification-1","repo_url":"https://github.com/seongminp/lime","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":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"weakly-supervised-classification","task_name":"Weakly Supervised Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"lime","method_name":"LIME"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.06720","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}