A Model of Zero-Shot Learning of Spoken Language Understanding

By Majid Yazdani, James Henderson. 2015

65 citations recorded by the source corpus.

When building spoken dialogue systems for a new domain, a major bottleneck is developing a spoken language understanding (SLU) module that handles the new domain’s terminology and semantic concepts. We propose a statistical SLU model that generalises to both previously unseen input words and previously unseen output classes by leveraging unlabelled data. After mapping the utterance into a vector space, the model exploits the structure of the output labels by mapping each label to a hyperplane that separates utterances with and without that label. Both these mappings are initialised with unsupervised word embeddings, so they can be computed even for words or concepts which were not in the SLU training data.

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

1. Philip S. Yu
2. 刘晗
3. Xiaotong Zhang
4. Congying Xia
5. Su Zhu
6. Lu Fan
7. Yi Chang
8. Xuandi Fu

Citations in the corpus

• Reconstructing Capsule Networks for Zero-shot Intent Classification (2019, background): “Ferreira et al. (2015a,b) and Yazdani and Henderson (2015) utilize external resources such as label ontologies or manually defined attributes to find the relationship between seen and unseen intent labels.”
• Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification (2020, methodology): “Early methods (Ferreira et al., 2015a,b; Yazdani and Henderson, 2015) explore the relationship between seen and unseen intents by introducing external resources such as manually defined attributes or label ontologies, but they are usually expensive to obtain.”
• Zero-shot User Intent Detection via Capsule Neural Networks (2018, background): “, 2015a,b) or manually defined attributes that describe intents (Yazdani and Henderson, 2015) to associate existing and emerging intents, which require extra annotation.”
• Data Augmentation with Atomic Templates for Spoken Language Understanding (2019, methodology): “• ZS: zero-shot learning of SLU (Yazdani and Henderson, 2015) which can adapt to unseen dialogue acts.”
• A Survey of Zero-Shot Learning (2019, methodology): “When learning the classifier, existing methods either treat each class label individually [14, 99, 100, 168] or exploit multilabel correlations [44, 84, 107, 126, 172].”