{"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/a-unified-pre-training-framework-for","title":"A Unified Pre-training Framework for Conversational AI","arxiv_id":"2105.02482","date":"2021-05-06","proceeding":null,"authors":["Siqi Bao","Bingjin Chen","Huang He","Xin Tian","Han Zhou","Fan Wang","Hua Wu","Haifeng Wang","Wenquan Wu","Yingzhan Lin"],"abstract":"In this work, we explore the application of PLATO-2 on various dialogue systems, including open-domain conversation, knowledge grounded dialogue, and task-oriented conversation. PLATO-2 is initially designed as an open-domain chatbot, trained via two-stage curriculum learning. In the first stage, a coarse-grained response generation model is learned to fit the simplified one-to-one mapping relationship. This model is applied to the task-oriented conversation, given that the semantic mappings tend to be deterministic in task completion. In the second stage, another fine-grained generation model and an evaluation model are further learned for diverse response generation and coherence estimation, respectively. With superior capability on capturing one-to-many mapping, such models are suitable for the open-domain conversation and knowledge grounded dialogue. For the comprehensive evaluation of PLATO-2, we have participated in multiple tasks of DSTC9, including interactive evaluation of open-domain conversation (Track3-task2), static evaluation of knowledge grounded dialogue (Track3-task1), and end-to-end task-oriented conversation (Track2-task1). PLATO-2 has obtained the 1st place in all three tasks, verifying its effectiveness as a unified framework for various dialogue systems.","url_abs":"https://arxiv.org/abs/2105.02482v2","url_pdf":"https://arxiv.org/pdf/2105.02482v2.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":"a-unified-pre-training-framework-for","repo_url":"https://github.com/PaddlePaddle/Knover","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"chatbot","task_name":"Chatbot"},{"task_slug":"interactive-evaluation-of-dialog","task_name":"Interactive Evaluation of Dialog"},{"task_slug":"response-generation","task_name":"Response Generation"}],"methods":[{"method_slug":"plato-2","method_name":"PLATO-2"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/interactive-evaluation-of-dialog-on-dstc9","task":"Interactive Evaluation of Dialog","dataset":"DSTC9 Track 3 - Task 2","model":"PLATO-2","rank_in_archive_order":1,"of":1,"metrics":{"Coherent":"2.8017","Consistent":"0.9390","Diversity":"2.7441","Error Recovery":" 2.7518","Flexible":"2.8000","Informative":"2.7881","Inquisitive":"2.7949","Likeable":"2.7878","Overall Human Rating":"4.15","Topic Depth":"2.7678","Understanding":"2.8285"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.02482","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}