Joint Slot Filling and Intent Detection via Capsule Neural Networks
By Chenwei Zhang, Yaliang Li, Nan Du, Wei Fan, Philip S. Yu. 2018
253 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections (2020, background): “…real-world applications such as fake news detection (Shu et al., 2017), document classification (Yang et al., 2016), and spoken language understanding (SLU) (Gupta et al., 2019a; Gupta et al., 2019b; Zhang et al., 2018), a core task of conversational assistants like Amazon Alexa or Google Assistant.”
- A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding (2019, background): “Zhang et al. (2019) propose a hierarchical capsule neural network to model the the hierarchical relationship among word, slot, and intent in an utterance.”
- CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection (2020, background): “State-of-the-art intent detection models (Haihong et al., 2019; Zhang et al., 2018; Goo et al., 2018) capitalize on large amounts of labeled data to train supervised deep learning classification models.”
- Don’t Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing (2020, methodology): “cy over existing baselines (+7.7% and +4.5% respectively.) Using a BERT encoder causes a slight decrease in performance, but still achieves a meaningful improvement over the previous state of the art [36]; this is consistent with what has been observed on other NLP tasks [17]. If no pretraining is u”