{"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/plato-pre-trained-dialogue-generation-model","title":"PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable","arxiv_id":"1910.07931","date":"2019-10-17","proceeding":"ACL 2020 6","authors":["Siqi Bao","Huang He","Fan Wang","Hua Wu","Haifeng Wang"],"abstract":"Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including chit-chat, knowledge grounded dialogues, and conversational question answering. In this framework, we adopt flexible attention mechanisms to fully leverage the bi-directional context and the uni-directional characteristic of language generation. We also introduce discrete latent variables to tackle the inherent one-to-many mapping problem in response generation. Two reciprocal tasks of response generation and latent act recognition are designed and carried out simultaneously within a shared network. Comprehensive experiments on three publicly available datasets verify the effectiveness and superiority of the proposed framework.","url_abs":"https://arxiv.org/abs/1910.07931v3","url_pdf":"https://arxiv.org/pdf/1910.07931v3.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":"plato-pre-trained-dialogue-generation-model","repo_url":"https://github.com/PaddlePaddle/Research","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"plato-pre-trained-dialogue-generation-model","repo_url":"https://github.com/egillian1/AblationPLATO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"plato-pre-trained-dialogue-generation-model","repo_url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/dialogue/plato-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"conversational-question-answering","task_name":"Conversational Question Answering"},{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.07931","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}