Existing approaches have achieved perfect scores on the benchmarkdatasets. However they are not suitable for deployment on low-resource devices like mobiles, tablets, etc. due to their massive model size . 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. We also report that our model has tiny memory footprint of ~5 MB andlow inference time of ~2 milliseconds, which proves its efficiency in aresource-constrained environment.

Author(s) : Sudeep Deepak Shivnikar, Himanshu Arora, Harichandana B S S

Links : PDF - Abstract

Code :

Keywords : character - device - classification - intent - representation -

Leave a Reply

Your email address will not be published. Required fields are marked *