{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/a-two-stage-prediction-aware-contrastive","title":"A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU","arxiv_id":"2405.02925","date":"2024-05-05","proceeding":null,"authors":["Guanhua Chen","Yutong Yao","Derek F. Wong","Lidia S. Chao"],"abstract":"Multi-intent natural language understanding (NLU) presents a formidable challenge due to the model confusion arising from multiple intents within a single utterance. While previous works train the model contrastively to increase the margin between different multi-intent labels, they are less suited to the nuances of multi-intent NLU. They ignore the rich information between the shared intents, which is beneficial to constructing a better embedding space, especially in low-data scenarios. We introduce a two-stage Prediction-Aware Contrastive Learning (PACL) framework for multi-intent NLU to harness this valuable knowledge. Our approach capitalizes on shared intent information by integrating word-level pre-training and prediction-aware contrastive fine-tuning. We construct a pre-training dataset using a word-level data augmentation strategy. Subsequently, our framework dynamically assigns roles to instances during contrastive fine-tuning while introducing a prediction-aware contrastive loss to maximize the impact of contrastive learning. We present experimental results and empirical analysis conducted on three widely used datasets, demonstrating that our method surpasses the performance of three prominent baselines on both low-data and full-data scenarios.","url_abs":"https://arxiv.org/abs/2405.02925v1","url_pdf":"https://arxiv.org/pdf/2405.02925v1.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":[],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"intent-detection","task_name":"Intent Detection"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"semantic-frame-parsing","task_name":"Semantic Frame Parsing"},{"task_slug":"slot-filling","task_name":"Slot Filling"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/intent-detection-on-mixatis","task":"Intent Detection","dataset":"MixATIS","model":"TFMN (PACL)","rank_in_archive_order":3,"of":15,"metrics":{"Accuracy":"82.9"},"uses_additional_data":false},{"leaderboard":"/sota/intent-detection-on-mixatis","task":"Intent Detection","dataset":"MixATIS","model":"SLIM (PACL)","rank_in_archive_order":4,"of":15,"metrics":{"Accuracy":"81.9"},"uses_additional_data":false},{"leaderboard":"/sota/intent-detection-on-mixatis","task":"Intent Detection","dataset":"MixATIS","model":"RoBERTa (PACL)","rank_in_archive_order":7,"of":15,"metrics":{"Accuracy":"79.1"},"uses_additional_data":false},{"leaderboard":"/sota/intent-detection-on-mixsnips","task":"Intent Detection","dataset":"MixSNIPS","model":"TFMN (PACL)","rank_in_archive_order":6,"of":16,"metrics":{"Accuracy":"97.4"},"uses_additional_data":false},{"leaderboard":"/sota/intent-detection-on-mixsnips","task":"Intent Detection","dataset":"MixSNIPS","model":"SLIM (PACL)","rank_in_archive_order":10,"of":16,"metrics":{"Accuracy":"96.9"},"uses_additional_data":false},{"leaderboard":"/sota/intent-detection-on-mixsnips","task":"Intent Detection","dataset":"MixSNIPS","model":"RoBERTa (PACL)","rank_in_archive_order":13,"of":16,"metrics":{"Accuracy":"96.5"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-mixatis","task":"Slot Filling","dataset":"MixATIS","model":"SLIM (PACL)","rank_in_archive_order":13,"of":15,"metrics":{"Micro F1":"87.3"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-mixatis","task":"Slot Filling","dataset":"MixATIS","model":"TFMN (PACL)","rank_in_archive_order":14,"of":15,"metrics":{"Micro F1":"86.7"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-mixatis","task":"Slot Filling","dataset":"MixATIS","model":"RoBERTa (PACL)","rank_in_archive_order":15,"of":15,"metrics":{"Micro F1":"86.0"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-mixsnips","task":"Slot Filling","dataset":"MixSNIPS","model":"SLIM (PACL)","rank_in_archive_order":2,"of":16,"metrics":{"Micro F1":"96.8"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-mixsnips","task":"Slot Filling","dataset":"MixSNIPS","model":"TFMN (PACL)","rank_in_archive_order":6,"of":16,"metrics":{"Micro F1":"96.3"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-mixsnips","task":"Slot Filling","dataset":"MixSNIPS","model":"RoBERTa (PACL)","rank_in_archive_order":7,"of":16,"metrics":{"Micro F1":"96.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.02925","atlas_url":"https://app.syntology.ai/?focus=2405.02925","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2405.02925"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2405.02925\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2405.02925"},"call":"get_concepts_for_paper(arxiv_id=\"2405.02925\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c6c8c6d36ea15ce52f85d1b192d7f5ff5e705e344d00868efc64a7f0617cf461","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}