{"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/large-scale-multi-domain-belief-tracking-with","title":"Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing","arxiv_id":"1807.06517","date":"2018-07-17","proceeding":"ACL 2018 7","authors":["Osman Ramadan","Paweł Budzianowski","Milica Gašić"],"abstract":"Robust dialogue belief tracking is a key component in maintaining good\nquality dialogue systems. The tasks that dialogue systems are trying to solve\nare becoming increasingly complex, requiring scalability to multi domain,\nsemantically rich dialogues. However, most current approaches have difficulty\nscaling up with domains because of the dependency of the model parameters on\nthe dialogue ontology. In this paper, a novel approach is introduced that fully\nutilizes semantic similarity between dialogue utterances and the ontology\nterms, allowing the information to be shared across domains. The evaluation is\nperformed on a recently collected multi-domain dialogues dataset, one order of\nmagnitude larger than currently available corpora. Our model demonstrates great\ncapability in handling multi-domain dialogues, simultaneously outperforming\nexisting state-of-the-art models in single-domain dialogue tracking tasks.","url_abs":"http://arxiv.org/abs/1807.06517v1","url_pdf":"http://arxiv.org/pdf/1807.06517v1.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":"large-scale-multi-domain-belief-tracking-with","repo_url":"https://github.com/jojonki/MultiWOZ-Parser","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"large-scale-multi-domain-belief-tracking-with","repo_url":"https://github.com/osmanio2/multi-domain-belief-tracking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multi-domain-dialogue-state-tracking","task_name":"Multi-domain Dialogue State Tracking"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.06517","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}