Reducing Model Jitter: Stable Re-training of Semantic Parsers in Production Environments

Understand

Retraining modern deep learning systems can lead to variations in model performance even when trained using the same data and hyper-parameters by simply using different random seeds.

• We call this phenomenon model jitter.
• This issue is often exacerbated in production settings, where models are retrained on noisy data.
• In this work we tackle the problem of stable retraining with a focus on conversational semantic parsers.