16th Annual Conference of the International Speech Communication Association

Dresden, Germany
September 6-10, 2015

RNN-Based Labeled Data Generation for Spoken Language Understanding

Yik-Cheung Tam, Yangyang Shi, Hunk Chen, Mei-Yuh Hwang

Microsoft, China

In spoken language understanding, getting manually labeled data such as domain, intent and slot labels is usually required for training classifiers. Starting with some manually labeled data, we propose a data generation approach to augment the training set with synthetic data sampled from a joint distribution between an input query and an output label. We propose using a recurrent neural network to model the joint distribution and sample synthetic data for classifier training. Evaluated on ATIS and live logs of Cortana, a Microsoft voice personal assistant, we showed consistent performance improvement on domain classification, intent classification, and slot tagging on multiple languages.

Full Paper

Bibliographic reference.  Tam, Yik-Cheung / Shi, Yangyang / Chen, Hunk / Hwang, Mei-Yuh (2015): "RNN-based labeled data generation for spoken language understanding", In INTERSPEECH-2015, 125-129.