A character representation enhanced on-device Intent Classification
This addresses the deployment challenge for intent classification on mobile and tablet devices, though it appears incremental as it builds on existing approaches with efficiency improvements.
The paper tackles the problem of deploying intent classification models on low-resource devices by proposing a lightweight architecture that uses character features to enrich word representations. The model achieves state-of-the-art results on benchmark datasets with a memory footprint of ~5 MB and inference time of ~2 milliseconds.
Intent classification is an important task in natural language understanding systems. Existing approaches have achieved perfect scores on the benchmark datasets. However they are not suitable for deployment on low-resource devices like mobiles, tablets, etc. due to their massive model size. Therefore, in this paper, we present a novel light-weight architecture for intent classification that can run efficiently on a device. We use character features to enrich the word representation. Our experiments prove that our proposed model outperforms existing approaches and achieves state-of-the-art results on benchmark datasets. We also report that our model has tiny memory footprint of ~5 MB and low inference time of ~2 milliseconds, which proves its efficiency in a resource-constrained environment.