{"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/few-shot-text-classification-with-induction","title":"Induction Networks for Few-Shot Text Classification","arxiv_id":"1902.10482","date":"2019-02-27","proceeding":"IJCNLP 2019 11","authors":["Ruiying Geng","Binhua Li","Yongbin Li","Xiaodan Zhu","Ping Jian","Jian Sun"],"abstract":"Text classification tends to struggle when data is deficient or when it needs to adapt to unseen classes. In such challenging scenarios, recent studies have used meta-learning to simulate the few-shot task, in which new queries are compared to a small support set at the sample-wise level. However, this sample-wise comparison may be severely disturbed by the various expressions in the same class. Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries. In this paper, we propose a novel Induction Network to learn such a generalized class-wise representation, by innovatively leveraging the dynamic routing algorithm in meta-learning. In this way, we find the model is able to induce and generalize better. We evaluate the proposed model on a well-studied sentiment classification dataset (English) and a real-world dialogue intent classification dataset (Chinese). Experiment results show that on both datasets, the proposed model significantly outperforms the existing state-of-the-art approaches, proving the effectiveness of class-wise generalization in few-shot text classification.","url_abs":"https://arxiv.org/abs/1902.10482v2","url_pdf":"https://arxiv.org/pdf/1902.10482v2.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":"few-shot-text-classification-with-induction","repo_url":"https://github.com/hongshengxin/Induction_network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"few-shot-text-classification-with-induction","repo_url":"https://github.com/laohur/LearnToCompareText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"few-shot-text-classification-with-induction","repo_url":"https://github.com/laohur/RelationNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"few-shot-text-classification-with-induction","repo_url":"https://github.com/mhw32/prototransformer-public","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"few-shot-text-classification-with-induction","repo_url":"https://github.com/zhongyuchen/few-shot-text-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-text-classification","task_name":"Few-Shot Text Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"intent-classification","task_name":"Intent Classification"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"intent-classification-1","task_name":"intent-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-text-classification-on-odic-10-way","task":"Few-Shot Text Classification","dataset":"ODIC 10-way (10-shot)","model":"Induction Networks","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"81.64"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-text-classification-on-odic-10-way-5","task":"Few-Shot Text Classification","dataset":"ODIC 10-way (5-shot)","model":"Induction Networks","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"78.27"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-text-classification-on-odic-5-way-10","task":"Few-Shot Text Classification","dataset":"ODIC 5-way (10-shot)","model":"Induction Networks","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"88.49"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-text-classification-on-odic-5-way-5","task":"Few-Shot Text Classification","dataset":"ODIC 5-way (5-shot)","model":"Induction Networks","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"87.16"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.10482","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}