{"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/train-once-test-anywhere-zero-shot-learning","title":"Train Once, Test Anywhere: Zero-Shot Learning for Text Classification","arxiv_id":"1712.05972","date":"2017-12-16","proceeding":null,"authors":["Pushpankar Kumar Pushp","Muktabh Mayank Srivastava"],"abstract":"Zero-shot Learners are models capable of predicting unseen classes. In this\nwork, we propose a Zero-shot Learning approach for text categorization. Our\nmethod involves training model on a large corpus of sentences to learn the\nrelationship between a sentence and embedding of sentence's tags. Learning such\nrelationship makes the model generalize to unseen sentences, tags, and even new\ndatasets provided they can be put into same embedding space. The model learns\nto predict whether a given sentence is related to a tag or not; unlike other\nclassifiers that learn to classify the sentence as one of the possible classes.\nWe propose three different neural networks for the task and report their\naccuracy on the test set of the dataset used for training them as well as two\nother standard datasets for which no retraining was done. We show that our\nmodels generalize well across new unseen classes in both cases. Although the\nmodels do not achieve the accuracy level of the state of the art supervised\nmodels, yet it evidently is a step forward towards general intelligence in\nnatural language processing.","url_abs":"http://arxiv.org/abs/1712.05972v2","url_pdf":"http://arxiv.org/pdf/1712.05972v2.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":"train-once-test-anywhere-zero-shot-learning","repo_url":"https://github.com/adamlin120/Zero-shot_Classification_of_News_Title","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"tag","task_name":"TAG"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.05972","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}