{"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/xl-nbt-a-cross-lingual-neural-belief-tracking","title":"XL-NBT: A Cross-lingual Neural Belief Tracking Framework","arxiv_id":"1808.06244","date":"2018-08-19","proceeding":"EMNLP 2018 10","authors":["Wenhu Chen","Jianshu Chen","Yu Su","Xin Wang","Dong Yu","Xifeng Yan","William Yang Wang"],"abstract":"Task-oriented dialog systems are becoming pervasive, and many companies\nheavily rely on them to complement human agents for customer service in call\ncenters. With globalization, the need for providing cross-lingual customer\nsupport becomes more urgent than ever. However, cross-lingual support poses\ngreat challenges---it requires a large amount of additional annotated data from\nnative speakers. In order to bypass the expensive human annotation and achieve\nthe first step towards the ultimate goal of building a universal dialog system,\nwe set out to build a cross-lingual state tracking framework. Specifically, we\nassume that there exists a source language with dialog belief tracking\nannotations while the target languages have no annotated dialog data of any\nform. Then, we pre-train a state tracker for the source language as a teacher,\nwhich is able to exploit easy-to-access parallel data. We then distill and\ntransfer its own knowledge to the student state tracker in target languages. We\nspecifically discuss two types of common parallel resources: bilingual corpus\nand bilingual dictionary, and design different transfer learning strategies\naccordingly. Experimentally, we successfully use English state tracker as the\nteacher to transfer its knowledge to both Italian and German trackers and\nachieve promising results.","url_abs":"http://arxiv.org/abs/1808.06244v2","url_pdf":"http://arxiv.org/pdf/1808.06244v2.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":"xl-nbt-a-cross-lingual-neural-belief-tracking","repo_url":"https://github.com/wenhuchen/Cross-Lingual-NBT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.06244","atlas_url":"https://app.syntology.ai/?focus=1808.06244","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}