{"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-natural-language-generation-for-task","title":"Few-shot Natural Language Generation for Task-Oriented Dialog","arxiv_id":"2002.12328","date":"2020-02-27","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Baolin Peng","Chenguang Zhu","Chunyuan Li","Xiujun Li","Jinchao Li","Michael Zeng","Jianfeng Gao"],"abstract":"As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts a dialog act represented in a semantic form into a response in natural language. The success of traditional template-based or statistical models typically relies on heavily annotated data, which is infeasible for new domains. Therefore, it is pivotal for an NLG system to generalize well with limited labelled data in real applications. To this end, we present FewShotWoz, the first NLG benchmark to simulate the few-shot learning setting in task-oriented dialog systems. Further, we develop the SC-GPT model. It is pre-trained on a large set of annotated NLG corpus to acquire the controllable generation ability, and fine-tuned with only a few domain-specific labels to adapt to new domains. Experiments on FewShotWoz and the large Multi-Domain-WOZ datasets show that the proposed SC-GPT significantly outperforms existing methods, measured by various automatic metrics and human evaluations.","url_abs":"https://arxiv.org/abs/2002.12328v1","url_pdf":"https://arxiv.org/pdf/2002.12328v1.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-natural-language-generation-for-task","repo_url":"https://github.com/pengbaolin/SC-GPT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"few-shot-natural-language-generation-for-task","repo_url":"https://github.com/pengbaolin/soloist","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-to-text-generation","task_name":"Data-to-Text Generation"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"sc-gpt","method_name":"SC-GPT"}],"datasets_introduced":[],"methods_introduced":[{"slug":"sc-gpt","name":"SC-GPT","full_name":"SC-GPT"}],"results":[{"leaderboard":"/sota/data-to-text-generation-on-multiwoz-2-1","task":"Data-to-Text Generation","dataset":"MULTIWOZ 2.1","model":"SC-GPT2","rank_in_archive_order":4,"of":5,"metrics":{"BLEU":"30.76"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.12328","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}