{"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/td-gin-token-level-dynamic-graph-interactive","title":"AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling","arxiv_id":"2004.10087","date":"2020-04-21","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Libo Qin","Xiao Xu","Wanxiang Che","Ting Liu"],"abstract":"In real-world scenarios, users usually have multiple intents in the same utterance. Unfortunately, most spoken language understanding (SLU) models either mainly focused on the single intent scenario, or simply incorporated an overall intent context vector for all tokens, ignoring the fine-grained multiple intents information integration for token-level slot prediction. In this paper, we propose an Adaptive Graph-Interactive Framework (AGIF) for joint multiple intent detection and slot filling, where we introduce an intent-slot graph interaction layer to model the strong correlation between the slot and intents. Such an interaction layer is applied to each token adaptively, which has the advantage to automatically extract the relevant intents information, making a fine-grained intent information integration for the token-level slot prediction. Experimental results on three multi-intent datasets show that our framework obtains substantial improvement and achieves the state-of-the-art performance. In addition, our framework achieves new state-of-the-art performance on two single-intent datasets.","url_abs":"https://arxiv.org/abs/2004.10087v4","url_pdf":"https://arxiv.org/pdf/2004.10087v4.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":"td-gin-token-level-dynamic-graph-interactive","repo_url":"https://github.com/LooperXX/AGIF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"intent-detection","task_name":"Intent Detection"},{"task_slug":"semantic-frame-parsing","task_name":"Semantic Frame Parsing"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"slot-filling","task_name":"Slot Filling"},{"task_slug":"spoken-language-understanding","task_name":"Spoken Language Understanding"},{"task_slug":"slot-filling-1","task_name":"slot-filling"}],"methods":[],"datasets_introduced":[{"slug":"mixatis","name":"MixATIS","full_name":""},{"slug":"mixsnips","name":"MixSNIPS","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/intent-detection-on-atis","task":"Intent Detection","dataset":"ATIS","model":"AGIF","rank_in_archive_order":13,"of":16,"metrics":{"Accuracy":"97.1"},"uses_additional_data":false},{"leaderboard":"/sota/intent-detection-on-mixsnips","task":"Intent Detection","dataset":"MixSNIPS","model":"AGIF","rank_in_archive_order":12,"of":16,"metrics":{"Accuracy":"96.5","f1 macro":"98.6"},"uses_additional_data":false},{"leaderboard":"/sota/intent-detection-on-snips","task":"Intent Detection","dataset":"SNIPS","model":"AGIF","rank_in_archive_order":4,"of":10,"metrics":{"Accuracy":"98.1"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-atis","task":"Slot Filling","dataset":"ATIS","model":"AGIF","rank_in_archive_order":7,"of":14,"metrics":{"F1":"0.96"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-mixsnips","task":"Slot Filling","dataset":"MixSNIPS","model":"AGIF","rank_in_archive_order":15,"of":16,"metrics":{"Micro F1":"94.5"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-snips","task":"Slot Filling","dataset":"SNIPS","model":"AGIF","rank_in_archive_order":4,"of":10,"metrics":{"F1":"94.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.10087","atlas_url":"https://app.syntology.ai/?focus=2004.10087","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}