Joint Slot Filling and Intent Detection via Capsule Neural Networks
Not on the map. Why?
Abstract (arXiv)
Being able to recognize words as slots and detect the intent of an utterance has been a keen issue in natural language understanding. The existing works either treat slot filling and intent detection separately in a pipeline manner, or adopt joint models which sequentially label slots while summarizing the utterance-level intent without explicitly preserving the hierarchical relationship among words, slots, and intents. To exploit the semantic hierarchy for effective modeling, we propose a capsule-based neural network model which accomplishes slot filling and intent detection via a dynamic routing-by-agreement schema. A re-routing schema is proposed to further synergize the slot filling performance using the inferred intent representation. Experiments on two real-world datasets show the effectiveness of our model when compared with other alternative model architectures, as well as existing natural language understanding services.
Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Dec 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 27; 2022: 24; 2023: 11; 2024: 9; 2025: 1; 2026: 1.
73 papers.
Sort:
By area:
- 2021A Survey on Spoken Language Understanding: Recent Advances and New Frontierscited by 53
- 2021Visual Goal-Step Inference using wikiHowcited by 42
- 2022A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methodscited by 42
- 2022MIntRec: A New Dataset for Multimodal Intent Recognitioncited by 41
- 2021GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Fillingcited by 33
- 2024MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversationscited by 25
- 2021Generalized Zero-shot Intent Detection via Commonsense Knowledgecited by 21
- 2021Intent Detection and Slot Filling for Vietnamesecited by 19
- 2023CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Taskscited by 18
- 2021Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialogcited by 17
- 2022Learning Discriminative Representations and Decision Boundaries for Open Intent Detectioncited by 15
- 2021CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detectioncited by 14
38 more
- 2022Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphscited by 14
- 2021Linguistically-Enriched and Context-Aware Zero-shot Slot Fillingcited by 12
- 2021Lifelong Intent Detection via Multi-Strategy Rebalancingcited by 12
- 2022Workflow Discovery from Dialogues in the Low Data Regimecited by 12
- 2021Towards Joint Intent Detection and Slot Filling via Higher-order Attentioncited by 11
- 2021SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Fillingcited by 10
- 2022Learning with Capsules: A Surveycited by 10
- 2022Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Fillingcited by 10
- 2021Distilling EEG Representations via Capsules for Affective Computingcited by 8
- 2022Bi-directional Joint Neural Networks for Intent Classification and Slot Fillingcited by 8
- 2023Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understandingcited by 7
- 2023MISCA: A Joint Model for Multiple Intent Detection and Slot Filling with Intent-Slot Co-Attentioncited by 7
- 2024ECLM: Entity Level Language Model for Spoken Language Understanding with Chain of Intentcited by 7
- 2021Masked Conditional Random Fields for Sequence Labelingcited by 6
- 2021Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Fillingcited by 6
- 2021A Question-answering Based Framework for Relation Extraction Validationcited by 5
- 2021An Effective Non-Autoregressive Model for Spoken Language Understandingcited by 5
- 2022Learning to Classify Open Intent via Soft Labeling and Manifold Mixupcited by 5
- 2022Explainable Slot Type Attentions to Improve Joint Intent Detection and Slot Fillingcited by 5
- 2024Medical Dialogue: A Survey of Categories, Methods, Evaluation and Challengescited by 5
- 2021Joint Intent Detection And Slot Filling Based on Continual Learning Modelcited by 4
- 2021A Result based Portable Framework for Spoken Language Understandingcited by 4
- 2021X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsingcited by 4
- 2022On the cross-lingual transferability of multilingual prototypical models across NLU taskscited by 4
- 2023Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive Learningcited by 4
- 2021An Adversarial Learning based Multi-Step Spoken Language Understanding System through Human-Computer Interactioncited by 3
- 2021LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Networkcited by 3
- 2022A Unified Framework for Multi-intent Spoken Language Understanding with promptingcited by 3
- 2022Learning Better Intent Representations for Financial Open Intent Classificationcited by 3
- 2022A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understandingcited by 3
- 2023Intent Detection and Slot Filling for Home Assistants: Dataset and Analysis for Bangla and Sylheticited by 3
- 2024CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understandingcited by 3
- 2022Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Taskcited by 2
- 2022Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Losscited by 2
- 2022Capture Salient Historical Information: A Fast and Accurate Non-Autoregressive Model for Multi-turn Spoken Language Understandingcited by 2
- 2022From Disfluency Detection to Intent Detection and Slot Fillingcited by 2
- 2022In-game Toxic Language Detection: Shared Task and Attention Residualscited by 2
- 2022A Transformer-Based User Satisfaction Prediction for Proactive Interaction Mechanism in DuerOScited by 2
50 most cited of 73 All 73 (JSON)
- 2026In-game Toxic Detection: Bi-directional Representations with Attention Residuals28 Sep 2026
- 2025Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction24 May 2025
- 2024CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding15 Jun 2024
- 2024Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning31 May 2024
- 2024Medical Dialogue: A Survey of Categories, Methods, Evaluation and Challenges17 May 2024
- 2024HC2L: Hybrid and Cooperative Contrastive Learning for Cross-lingual Spoken Language Understanding10 May 2024
- 2024A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU5 May 2024
- 2024MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations16 Mar 2024
- 2024ECLM: Entity Level Language Model for Spoken Language Understanding with Chain of Intent7 Mar 2024
- 2024Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task22 Feb 2024
- 2024Pro-HAN: A Heterogeneous Graph Attention Network for Profile-Based Spoken Language Understanding6 Feb 2024
- 2023JPIS: A Joint Model for Profile-based Intent Detection and Slot Filling with Slot-to-Intent Attention14 Dec 2023
38 more
- 2023MISCA: A Joint Model for Multiple Intent Detection and Slot Filling with Intent-Slot Co-Attention10 Dec 2023
- 2023Co-guiding for Multi-intent Spoken Language Understanding22 Nov 2023
- 2023CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks23 Oct 2023
- 2023Intent Detection and Slot Filling for Home Assistants: Dataset and Analysis for Bangla and Sylheti17 Oct 2023
- 2023RSVP: Customer Intent Detection via Agent Response Contrastive and Generative Pre-Training15 Oct 2023
- 2023Explainable and Accurate Natural Language Understanding for Voice Assistants and Beyond25 Sep 2023
- 2023Introducing "Forecast Utterance" for Conversational Data Science7 Sep 2023
- 2023Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive Learning9 Aug 2023
- 2023Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understanding15 Jun 2023
- 2023Toward Open-domain Slot Filling via Self-supervised Co-training24 Mar 2023
- 2022A Robust Semantic Frame Parsing Pipeline on a New Complex Twitter Dataset18 Dec 2022
- 2022A Transformer-Based User Satisfaction Prediction for Proactive Interaction Mechanism in DuerOS5 Dec 2022
- 2022Zero-Shot Learning for Joint Intent and Slot Labeling29 Nov 2022
- 2022A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding22 Nov 2022
- 2022In-game Toxic Language Detection: Shared Task and Attention Residuals11 Nov 2022
- 2022Learning Better Intent Representations for Financial Open Intent Classification25 Oct 2022
- 2022Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs19 Oct 2022
- 2022Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling19 Oct 2022
- 2022Explainable Slot Type Attentions to Improve Joint Intent Detection and Slot Filling19 Oct 2022
- 2022A Unified Framework for Multi-intent Spoken Language Understanding with prompting7 Oct 2022
- 2022From Disfluency Detection to Intent Detection and Slot Filling17 Sep 2022
- 2022MIntRec: A New Dataset for Multimodal Intent Recognition9 Sep 2022
- 2022Multi-grained Label Refinement Network with Dependency Structures for Joint Intent Detection and Slot Filling9 Sep 2022
- 2022Entity Aware Syntax Tree Based Data Augmentation for Natural Language Understanding6 Sep 2022
- 2022On the cross-lingual transferability of multilingual prototypical models across NLU tasks19 Jul 2022
- 2022Capture Salient Historical Information: A Fast and Accurate Non-Autoregressive Model for Multi-turn Spoken Language Understanding24 Jun 2022
- 2022Learning with Capsules: A Survey6 Jun 2022
- 2022Workflow Discovery from Dialogues in the Low Data Regime24 May 2022
- 2022Learning to Classify Open Intent via Soft Labeling and Manifold Mixup16 Apr 2022
- 2022A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods7 Apr 2022
- 2022Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss17 Mar 2022
- 2022Learning Discriminative Representations and Decision Boundaries for Open Intent Detection11 Mar 2022
- 2022Bi-directional Joint Neural Networks for Intent Classification and Slot Filling26 Feb 2022
- 2022Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task7 Jan 2022
- 2021LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network6 Oct 2021
- 2021Towards Joint Intent Detection and Slot Filling via Higher-order Attention18 Sep 2021
- 2021Traffic Event Detection as a Slot Filling Problem13 Sep 2021
- 2021SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling26 Aug 2021
50 newest of 73 All 73 (JSON)
- 2021A Survey on Spoken Language Understanding: Recent Advances and New Frontierscited by 53
- 2021Visual Goal-Step Inference using wikiHowcited by 42
- 2022A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methodscited by 42
- 2022MIntRec: A New Dataset for Multimodal Intent Recognitioncited by 41
- 2021GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Fillingcited by 33
- 2024MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversationscited by 25
- 2021Generalized Zero-shot Intent Detection via Commonsense Knowledgecited by 21
- 2021Intent Detection and Slot Filling for Vietnamesecited by 19
- 2021Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialogcited by 17
- 2022Learning Discriminative Representations and Decision Boundaries for Open Intent Detectioncited by 15
- 2021CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detectioncited by 14
- 2022Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphscited by 14
12 most cited of 71 All 71 (JSON)
- 2026In-game Toxic Detection: Bi-directional Representations with Attention Residuals28 Sep 2026
- 2025Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction24 May 2025
- 2024CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding15 Jun 2024
- 2024Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning31 May 2024
- 2024Medical Dialogue: A Survey of Categories, Methods, Evaluation and Challenges17 May 2024
- 2024HC2L: Hybrid and Cooperative Contrastive Learning for Cross-lingual Spoken Language Understanding10 May 2024
- 2024A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU5 May 2024
- 2024MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations16 Mar 2024
- 2024ECLM: Entity Level Language Model for Spoken Language Understanding with Chain of Intent7 Mar 2024
- 2024Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task22 Feb 2024
- 2024Pro-HAN: A Heterogeneous Graph Attention Network for Profile-Based Spoken Language Understanding6 Feb 2024
- 2023JPIS: A Joint Model for Profile-based Intent Detection and Slot Filling with Slot-to-Intent Attention14 Dec 2023
12 newest of 71 All 71 (JSON)