{"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/learning-to-embed-multi-modal-contexts-for-1","title":"Learning to Embed Multi-Modal Contexts for Situated Conversational Agents","arxiv_id":null,"date":"2022-07-01","proceeding":"Findings (NAACL) 2022 7","authors":["Haeju Lee","Oh Joon Kwon","Yunseon Choi","Minho Park","Ran Han","Yoonhyung Kim","Jinhyeon Kim","Youngjune Lee","Haebin Shin","Kangwook Lee","Kee-Eung Kim"],"abstract":"The Situated Interactive Multi-Modal Conversations (SIMMC) 2.0 aims to create virtual shopping assistants that can accept complex multi-modal inputs, i.e. visual appearances of objects and user utterances. It consists of four subtasks, multi-modal disambiguation (MM-Disamb), multi-modal coreference resolution (MM-Coref), multi-modal dialog state tracking (MM-DST), and response retrieval and generation. While many task-oriented dialog systems usually tackle each subtask separately, we propose a jointly learned multi-modal encoder-decoder that incorporates visual inputs and performs all four subtasks at once for efficiency. This approach won the MM-Coref and response retrieval subtasks and nominated runner-up for the remaining subtasks using a single unified model at the 10th Dialog Systems Technology Challenge (DSTC10), setting a high bar for the novel task of multi-modal task-oriented dialog systems.","url_abs":"https://aclanthology.org/2022.findings-naacl.61","url_pdf":"https://aclanthology.org/2022.findings-naacl.61.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":[],"tasks":[{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"dialogue-state-tracking","task_name":"Dialogue State Tracking"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"coreference-resolution-1","task_name":"coreference-resolution"},{"task_slug":null,"task_name":"dialog state tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dialogue-state-tracking-on-simmc2-0","task":"Dialogue State Tracking","dataset":"SIMMC2.0","model":"BART-large","rank_in_archive_order":2,"of":5,"metrics":{"Act F1":"96.3","Slot F1":"88.3"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-state-tracking-on-simmc2-0","task":"Dialogue State Tracking","dataset":"SIMMC2.0","model":"BART-base","rank_in_archive_order":3,"of":5,"metrics":{"Act F1":"95.2","Slot F1":"82.0 "},"uses_additional_data":false},{"leaderboard":"/sota/response-generation-on-simmc2-0","task":"Response Generation","dataset":"SIMMC2.0","model":"BART-large","rank_in_archive_order":2,"of":5,"metrics":{"BLEU":"33.1"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}