{"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/hierarchical-pointer-generator-memory-network","title":"Disentangling Language and Knowledge in Task-Oriented Dialogs","arxiv_id":"1805.01216","date":"2018-05-03","proceeding":"NAACL 2019 6","authors":["Dinesh Raghu","Nikhil Gupta","Mausam"],"abstract":"The Knowledge Base (KB) used for real-world applications, such as booking a\nmovie or restaurant reservation, keeps changing over time. End-to-end neural\nnetworks trained for these task-oriented dialogs are expected to be immune to\nany changes in the KB. However, existing approaches breakdown when asked to\nhandle such changes. We propose an encoder-decoder architecture (BoSsNet) with\na novel Bag-of-Sequences (BoSs) memory, which facilitates the disentangled\nlearning of the response's language model and its knowledge incorporation.\nConsequently, the KB can be modified with new knowledge without a drop in\ninterpretability. We find that BoSsNet outperforms state-of-the-art models,\nwith considerable improvements (> 10\\%) on bAbI OOV test sets and other\nhuman-human datasets. We also systematically modify existing datasets to\nmeasure disentanglement and show BoSsNet to be robust to KB modifications.","url_abs":"http://arxiv.org/abs/1805.01216v3","url_pdf":"http://arxiv.org/pdf/1805.01216v3.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":"hierarchical-pointer-generator-memory-network","repo_url":"https://github.com/dair-iitd/BossNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.01216","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}