With the expanding role of voice-controlled devices, bootstrapping spoken language understanding models from little labeled data becomes essential. Semi-supervised learning is a common technique to improve model performance when labeled data is scarce. In a real-world production system, the labeled data and the online test data often may come from different distributions. In this work, we use semi-supervised learning based on pseudolabeling with an auxiliary task on incoming unlabeled noisy

more »

... , which is closer to the test distribution. We demonstrate empirically that our approach can mitigate negative effects arising from training with non-representative labeled data as well as the negative impacts of noises in the data, which are introduced by pseudo-labeling and automatic speech recognition.