{"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/topic-based-evaluation-for-conversational","title":"Topic-based Evaluation for Conversational Bots","arxiv_id":"1801.03622","date":"2018-01-11","proceeding":null,"authors":["Fenfei Guo","Angeliki Metallinou","Chandra Khatri","Anirudh Raju","Anu Venkatesh","Ashwin Ram"],"abstract":"Dialog evaluation is a challenging problem, especially for non task-oriented\ndialogs where conversational success is not well-defined. We propose to\nevaluate dialog quality using topic-based metrics that describe the ability of\na conversational bot to sustain coherent and engaging conversations on a topic,\nand the diversity of topics that a bot can handle. To detect conversation\ntopics per utterance, we adopt Deep Average Networks (DAN) and train a topic\nclassifier on a variety of question and query data categorized into multiple\ntopics. We propose a novel extension to DAN by adding a topic-word attention\ntable that allows the system to jointly capture topic keywords in an utterance\nand perform topic classification. We compare our proposed topic based metrics\nwith the ratings provided by users and show that our metrics both correlate\nwith and complement human judgment. Our analysis is performed on tens of\nthousands of real human-bot dialogs from the Alexa Prize competition and\nhighlights user expectations for conversational bots.","url_abs":"http://arxiv.org/abs/1801.03622v1","url_pdf":"http://arxiv.org/pdf/1801.03622v1.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":"topic-based-evaluation-for-conversational","repo_url":"https://github.com/knights207210/Deep-Learning-for-VUI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"topic-classification","task_name":"Topic Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1801.03622","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}