{"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/enhancing-joint-multiple-intent-detection-and","title":"Enhancing Joint Multiple Intent Detection and Slot Filling with Global Intent-Slot Co-occurrence","arxiv_id":null,"date":"2022-12-01","proceeding":"Conference on Empirical Methods in Natural Language Processing 2022 12","authors":["Mengxiao Song","Bowen Yu","Li Quangang","Wang Yubin","Tingwen Liu","Hongbo Xu"],"abstract":"Multi-intent detection and slot filling joint model attracts more and more attention since it can handle multi-intent utterances, which is closer to complex real-world scenarios. Most existing joint models rely entirely on the training procedure to obtain the implicit correlation between intents and slots. However, they ignore the fact that leveraging the rich global knowledge in the corpus can determine the intuitive and explicit correlation between intents and slots. In this paper, we aim to make full use of the statistical co-occurrence frequency between intents and slots as prior knowledge to enhance joint multiple intent detection and slot filling. To be specific, an intent-slot co-occurrence graph is constructed based on the entire training corpus to globally discover correlation between intents and slots. Based on the global intent-slot co-occurrence, we propose a novel graph neural network to model the interaction between the two subtasks. Experimental results on two public multi-intent datasets demonstrate that our approach outperforms the state-of-the-art models.","url_abs":"https://aclanthology.org/2022.emnlp-main.543/","url_pdf":"https://aclanthology.org/2022.emnlp-main.543.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":"enhancing-joint-multiple-intent-detection-and","repo_url":"https://github.com/smxiao/GISCo","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"intent-detection","task_name":"Intent Detection"},{"task_slug":"semantic-frame-parsing","task_name":"Semantic Frame Parsing"},{"task_slug":"slot-filling","task_name":"Slot Filling"},{"task_slug":"slot-filling-1","task_name":"slot-filling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/intent-detection-on-mixatis","task":"Intent Detection","dataset":"MixATIS","model":"Global Intent-Slot Co-occurence","rank_in_archive_order":14,"of":15,"metrics":{"Accuracy":"75.0"},"uses_additional_data":false},{"leaderboard":"/sota/intent-detection-on-mixsnips","task":"Intent Detection","dataset":"MixSNIPS","model":"Global Intent-Slot Co-occurence","rank_in_archive_order":16,"of":16,"metrics":{"Accuracy":"95.5"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-mixatis","task":"Slot Filling","dataset":"MixATIS","model":"Global Intent-Slot Co-occurence","rank_in_archive_order":8,"of":15,"metrics":{"Micro F1":"88.5"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-mixsnips","task":"Slot Filling","dataset":"MixSNIPS","model":"Global Intent-Slot Co-occurence","rank_in_archive_order":12,"of":16,"metrics":{"Micro F1":"95.0"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}