{"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/end-to-end-adversarial-learning-for","title":"End-to-end Adversarial Learning for Generative Conversational Agents","arxiv_id":"1711.10122","date":"2017-11-28","proceeding":null,"authors":["Oswaldo Ludwig"],"abstract":"This paper presents a new adversarial learning method for generative\nconversational agents (GCA) besides a new model of GCA. Similar to previous\nworks on adversarial learning for dialogue generation, our method assumes the\nGCA as a generator that aims at fooling a discriminator that labels dialogues\nas human-generated or machine-generated; however, in our approach, the\ndiscriminator performs token-level classification, i.e. it indicates whether\nthe current token was generated by humans or machines. To do so, the\ndiscriminator also receives the context utterances (the dialogue history) and\nthe incomplete answer up to the current token as input. This new approach makes\npossible the end-to-end training by backpropagation. A self-conversation\nprocess enables to produce a set of generated data with more diversity for the\nadversarial training. This approach improves the performance on questions not\nrelated to the training data. Experimental results with human and adversarial\nevaluations show that the adversarial method yields significant performance\ngains over the usual teacher forcing training.","url_abs":"http://arxiv.org/abs/1711.10122v3","url_pdf":"http://arxiv.org/pdf/1711.10122v3.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":"end-to-end-adversarial-learning-for","repo_url":"https://github.com/oswaldoludwig/Adversarial-Learning-for-Generative-Conversational-Agents","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"end-to-end-adversarial-learning-for","repo_url":"https://github.com/oswaldoludwig/Seq2seq-Chatbot-for-Keras","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"end-to-end-adversarial-learning-for","repo_url":"https://github.com/oswaldoludwig/Parallel-Seq2Seq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}