Joint Slot Filling and Intent Detection via Capsule Neural Networks
arXiv:1812.09471
Abstract
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.
arXiv commentIn ACL 2019 as a long paper. Code and data available at https://github.com/czhang99/Capsule-NLU
References in corpus (3)
Cited by in corpus (10)
- Deep Open Intent Classification with Adaptive Decision Boundary
- CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection
- Towards Open Intent Discovery for Conversational Text
- Distilling EEG Representations via Capsules for Affective Computing
- CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding
- Interactive Teaching for Conversational AI
- Linguistically-Enriched and Context-Aware Zero-shot Slot Filling
- An Adversarial Learning based Multi-Step Spoken Language Understanding System through Human-Computer Interaction
- Parallel Intent and Slot Prediction using MLB Fusion
- CASA-NLU: Context-Aware Self-Attentive Natural Language Understanding for Task-Oriented Chatbots