{"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/a-bi-model-based-rnn-semantic-frame-parsing","title":"A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling","arxiv_id":"1812.10235","date":"2018-12-26","proceeding":"NAACL 2018 6","authors":["Yu Wang","Yilin Shen","Hongxia Jin"],"abstract":"Intent detection and slot filling are two main tasks for building a spoken\nlanguage understanding(SLU) system. Multiple deep learning based models have\ndemonstrated good results on these tasks . The most effective algorithms are\nbased on the structures of sequence to sequence models (or \"encoder-decoder\"\nmodels), and generate the intents and semantic tags either using separate\nmodels or a joint model. Most of the previous studies, however, either treat\nthe intent detection and slot filling as two separate parallel tasks, or use a\nsequence to sequence model to generate both semantic tags and intent. Most of\nthese approaches use one (joint) NN based model (including encoder-decoder\nstructure) to model two tasks, hence may not fully take advantage of the\ncross-impact between them. In this paper, new Bi-model based RNN semantic frame\nparsing network structures are designed to perform the intent detection and\nslot filling tasks jointly, by considering their cross-impact to each other\nusing two correlated bidirectional LSTMs (BLSTM). Our Bi-model structure with a\ndecoder achieves state-of-the-art result on the benchmark ATIS data, with about\n0.5$\\%$ intent accuracy improvement and 0.9 $\\%$ slot filling improvement.","url_abs":"http://arxiv.org/abs/1812.10235v1","url_pdf":"http://arxiv.org/pdf/1812.10235v1.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":"a-bi-model-based-rnn-semantic-frame-parsing","repo_url":"https://github.com/ray075hl/Bi-Model-Intent-And-Slot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"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":"spoken-language-understanding","task_name":"Spoken Language Understanding"},{"task_slug":"model","task_name":"model"},{"task_slug":"slot-filling-1","task_name":"slot-filling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/intent-detection-on-atis","task":"Intent Detection","dataset":"ATIS","model":"Bi-model with decoder","rank_in_archive_order":1,"of":16,"metrics":{"Accuracy":"98.99"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-atis","task":"Slot Filling","dataset":"ATIS","model":"Bi-model with a decoder","rank_in_archive_order":2,"of":14,"metrics":{"F1":"0.9689"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.10235","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}