Abstract
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.- Anthology ID:
- 2020.icon-workshop.6
- Volume:
- Proceedings of the Workshop on Joint NLP Modelling for Conversational AI @ ICON 2020
- Month:
- December
- Year:
- 2020
- Address:
- Patna, India
- Editors:
- Praveen Kumar G S, Siddhartha Mukherjee, Ranjan Samal
- Venue:
- ICON
- SIG:
- Publisher:
- NLP Association of India (NLPAI)
- Note:
- Pages:
- 40–46
- Language:
- URL:
- https://aclanthology.org/2020.icon-workshop.6
- DOI:
- Cite (ACL):
- Sudeep Deepak Shivnikar, Himanshu Arora, and Harichandana B S S. 2020. A character representation enhanced on-device Intent Classification. In Proceedings of the Workshop on Joint NLP Modelling for Conversational AI @ ICON 2020, pages 40–46, Patna, India. NLP Association of India (NLPAI).
- Cite (Informal):
- A character representation enhanced on-device Intent Classification (Shivnikar et al., ICON 2020)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/2020.icon-workshop.6.pdf
- Data
- ATIS, SNIPS