{"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-knowledge-grounded-multimodal-search-based","title":"A Knowledge-Grounded Multimodal Search-Based Conversational Agent","arxiv_id":"1810.11954","date":"2018-10-20","proceeding":"WS 2018 10","authors":["Shubham Agarwal","Ondrej Dusek","Ioannis Konstas","Verena Rieser"],"abstract":"Multimodal search-based dialogue is a challenging new task: It extends\nvisually grounded question answering systems into multi-turn conversations with\naccess to an external database. We address this new challenge by learning a\nneural response generation system from the recently released Multimodal\nDialogue (MMD) dataset (Saha et al., 2017). We introduce a knowledge-grounded\nmultimodal conversational model where an encoded knowledge base (KB)\nrepresentation is appended to the decoder input. Our model substantially\noutperforms strong baselines in terms of text-based similarity measures (over 9\nBLEU points, 3 of which are solely due to the use of additional information\nfrom the KB.","url_abs":"http://arxiv.org/abs/1810.11954v1","url_pdf":"http://arxiv.org/pdf/1810.11954v1.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-knowledge-grounded-multimodal-search-based","repo_url":"https://github.com/shubhamagarwal92/mmd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"response-generation","task_name":"Response Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.11954","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}