{"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/what-makes-a-good-conversation-how","title":"What makes a good conversation? How controllable attributes affect human judgments","arxiv_id":"1902.08654","date":"2019-02-22","proceeding":"NAACL 2019 6","authors":["Abigail See","Stephen Roller","Douwe Kiela","Jason Weston"],"abstract":"A good conversation requires balance -- between simplicity and detail;\nstaying on topic and changing it; asking questions and answering them. Although\ndialogue agents are commonly evaluated via human judgments of overall quality,\nthe relationship between quality and these individual factors is less\nwell-studied. In this work, we examine two controllable neural text generation\nmethods, conditional training and weighted decoding, in order to control four\nimportant attributes for chitchat dialogue: repetition, specificity,\nresponse-relatedness and question-asking. We conduct a large-scale human\nevaluation to measure the effect of these control parameters on multi-turn\ninteractive conversations on the PersonaChat task. We provide a detailed\nanalysis of their relationship to high-level aspects of conversation, and show\nthat by controlling combinations of these variables our models obtain clear\nimprovements in human quality judgments.","url_abs":"http://arxiv.org/abs/1902.08654v2","url_pdf":"http://arxiv.org/pdf/1902.08654v2.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":"what-makes-a-good-conversation-how","repo_url":"https://github.com/HMJiangGatech/dialogue_ope_data","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"what-makes-a-good-conversation-how","repo_url":"https://github.com/passing2961/empgpt-3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"specificity","task_name":"Specificity"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1902.08654","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}